Daily Papers

World action models (WAMs) have recently shown promise in jointly modeling future observations and executable robot actions. However, most existing WAMs still operate in 2D video or latent spaces, where visually plausible rollouts miss the 3D spatial constraints and occluded contact geometry required for precise manipulation. While geometric foundation models offer strong priors for recovering dense 3D structure and motion from visual observations, forcing WAMs to predict the dense 4D representation introduces costly geometric decoding and slows down causal action generation. To address the trade-off, we present WAM4D, a fast 4D world action model that uses lightweight spatial register tokens as training-time future-depth readouts to transfer pretrained geometric priors into a causal video-action transformer, then removes the register branch for lightweight action inference. To prevent non-causal shortcuts, we further design causal mixture attention for the Mixture-of-Transformers (MoT) WAM backbone, defining modality-specific visibility among video, action, and geometry tokens. Comprehensive experiments on RoboTwin 2.0 and challenging real-world manipulation tasks show that WAM4D improves spatial consistency and achieves competitive action prediction while maintaining efficient inference.

Vision-Language-Action (VLA) models have emerged as a promising paradigm for robot learning, but their representations are still largely inherited from static image-text pretraining, leaving physical dynamics to be learned from comparatively limited action data. Generative video models, by contrast, encode rich spatiotemporal structure and implicit physics, making them a compelling foundation for robotic manipulation. But their potentials are not fully explored in the literature. To bridge the gap, we introduce DiT4DiT, an end-to-end Video-Action Model that couples a video Diffusion Transformer with an action Diffusion Transformer in a unified cascaded framework. Instead of relying on reconstructed future frames, DiT4DiT extracts intermediate denoising features from the video generation process and uses them as temporally grounded conditions for action prediction. We further propose a dual flow-matching objective with decoupled timesteps and noise scales for video prediction, hidden-state extraction, and action inference, enabling coherent joint training of both modules. Across simulation and real-world benchmarks, DiT4DiT achieves state-of-the-art results, reaching average success rates of 98.6% on LIBERO and 50.8% on RoboCasa GR1 while using substantially less training data. On the Unitree G1 robot, it also delivers superior real-world performance and strong zero-shot generalization. Importantly, DiT4DiT improves sample efficiency by over 10x and speeds up convergence by up to 7x, demonstrating that video generation can serve as an effective scaling proxy for robot policy learning. We release code and models at https://dit4dit.github.io/.

Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture temporal dynamics and motion priors that are naturally suited for driving. We present DriveWAM, a driving world-action model that adapts a pretrained video diffusion transformer into an autoregressive video-action policy. DriveWAM organizes video and action streams into a unified temporal token sequence and trains them under a joint flow-matching objective, preserving the pretrained video-generation architecture while adapting its large-scale video priors to action generation. To incorporate high-level scene understanding, we introduce scene-evolving driving guidance, where a frozen VLM produces chunk-specific semantic intent to guide video-action generation. To keep long-horizon rollout bounded, we further introduce selective KV memory, which maintains bounded modality-aware video and action memory pools through relevance-redundancy cache selection at inference time. Experiments on NAVSIM and the PhysicalAI-Autonomous-Vehicles benchmark show that DriveWAM achieves strong planning performance, and a data-scaling study from 4k to 100k driving clips further confirms the scaling potential of world-action modeling for end-to-end autonomous driving.

Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor identification. In this work, we propose an end-to-end framework for efficient video action detection (EVAD) based on vanilla ViTs. Our EVAD consists of two specialized designs for video action detection. First, we propose a spatiotemporal token dropout from a keyframe-centric perspective. In a video clip, we maintain all tokens from its keyframe, preserve tokens relevant to actor motions from other frames, and drop out the remaining tokens in this clip. Second, we refine scene context by leveraging remaining tokens for better recognizing actor identities. The region of interest (RoI) in our action detector is expanded into temporal domain. The captured spatiotemporal actor identity representations are refined via scene context in a decoder with the attention mechanism. These two designs make our EVAD efficient while maintaining accuracy, which is validated on three benchmark datasets (i.e., AVA, UCF101-24, JHMDB). Compared to the vanilla ViT backbone, our EVAD reduces the overall GFLOPs by 43% and improves real-time inference speed by 40% with no performance degradation. Moreover, even at similar computational costs, our EVAD can improve the performance by 1.1 mAP with higher resolution inputs. Code is available at https://github.com/MCG-NJU/EVAD.

Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture long-term dependency of input sequences. However, we found that these Video Transformers are still biased to learn spatial dynamics rather than temporal ones, and debiasing the spurious correlation is critical for their performance. Based on the observations, we design simple yet effective self-supervised tasks for video models to learn temporal dynamics better. Specifically, for debiasing the spatial bias, our method learns the temporal order of video frames as extra self-supervision and enforces the randomly shuffled frames to have low-confidence outputs. Also, our method learns the temporal flow direction of video tokens among consecutive frames for enhancing the correlation toward temporal dynamics. Under various video action recognition tasks, we demonstrate the effectiveness of our method and its compatibility with state-of-the-art Video Transformers.

This paper explores the impact of occlusions in video action detection. We facilitate this study by introducing five new benchmark datasets namely O-UCF and O-JHMDB consisting of synthetically controlled static/dynamic occlusions, OVIS-UCF and OVIS-JHMDB consisting of occlusions with realistic motions and Real-OUCF for occlusions in realistic-world scenarios. We formally confirm an intuitive expectation: existing models suffer a lot as occlusion severity is increased and exhibit different behaviours when occluders are static vs when they are moving. We discover several intriguing phenomenon emerging in neural nets: 1) transformers can naturally outperform CNN models which might have even used occlusion as a form of data augmentation during training 2) incorporating symbolic-components like capsules to such backbones allows them to bind to occluders never even seen during training and 3) Islands of agreement can emerge in realistic images/videos without instance-level supervision, distillation or contrastive-based objectives2(eg. video-textual training). Such emergent properties allow us to derive simple yet effective training recipes which lead to robust occlusion models inductively satisfying the first two stages of the binding mechanism (grouping/segregation). Models leveraging these recipes outperform existing video action-detectors under occlusion by 32.3% on O-UCF, 32.7% on O-JHMDB & 2.6% on Real-OUCF in terms of the vMAP metric. The code for this work has been released at https://github.com/rajatmodi62/OccludedActionBenchmark.

We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. Specifically, our Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal representations that are rich enough to benefit a variety of downstream tasks. We train VATT end-to-end from scratch using multimodal contrastive losses and evaluate its performance by the downstream tasks of video action recognition, audio event classification, image classification, and text-to-video retrieval. Furthermore, we study a modality-agnostic, single-backbone Transformer by sharing weights among the three modalities. We show that the convolution-free VATT outperforms state-of-the-art ConvNet-based architectures in the downstream tasks. Especially, VATT's vision Transformer achieves the top-1 accuracy of 82.1% on Kinetics-400, 83.6% on Kinetics-600, 72.7% on Kinetics-700, and 41.1% on Moments in Time, new records while avoiding supervised pre-training. Transferring to image classification leads to 78.7% top-1 accuracy on ImageNet compared to 64.7% by training the same Transformer from scratch, showing the generalizability of our model despite the domain gap between videos and images. VATT's audio Transformer also sets a new record on waveform-based audio event recognition by achieving the mAP of 39.4% on AudioSet without any supervised pre-training. VATT's source code is publicly available.

While a general embodied agent must function as a unified system, current methods are built on isolated models for understanding, world modeling, and control. This fragmentation prevents unifying multimodal generative capabilities and hinders learning from large-scale, heterogeneous data. In this paper, we propose Motus, a unified latent action world model that leverages existing general pretrained models and rich, sharable motion information. Motus introduces a Mixture-of-Transformer (MoT) architecture to integrate three experts (i.e., understanding, video generation, and action) and adopts a UniDiffuser-style scheduler to enable flexible switching between different modeling modes (i.e., world models, vision-language-action models, inverse dynamics models, video generation models, and video-action joint prediction models). Motus further leverages the optical flow to learn latent actions and adopts a recipe with three-phase training pipeline and six-layer data pyramid, thereby extracting pixel-level "delta action" and enabling large-scale action pretraining. Experiments show that Motus achieves superior performance against state-of-the-art methods in both simulation (a +15% improvement over X-VLA and a +45% improvement over Pi0.5) and real-world scenarios(improved by +11~48%), demonstrating unified modeling of all functionalities and priors significantly benefits downstream robotic tasks.

We introduce Iwin Transformer, a novel position-embedding-free hierarchical vision transformer, which can be fine-tuned directly from low to high resolution, through the collaboration of innovative interleaved window attention and depthwise separable convolution. This approach uses attention to connect distant tokens and applies convolution to link neighboring tokens, enabling global information exchange within a single module, overcoming Swin Transformer's limitation of requiring two consecutive blocks to approximate global attention. Extensive experiments on visual benchmarks demonstrate that Iwin Transformer exhibits strong competitiveness in tasks such as image classification (87.4 top-1 accuracy on ImageNet-1K), semantic segmentation and video action recognition. We also validate the effectiveness of the core component in Iwin as a standalone module that can seamlessly replace the self-attention module in class-conditional image generation. The concepts and methods introduced by the Iwin Transformer have the potential to inspire future research, like Iwin 3D Attention in video generation. The code and models are available at https://github.com/cominder/Iwin-Transformer.

Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities like that of human beings. This paper aims to explore large-scale models in computer vision. We tackle three major issues in training and application of large vision models, including training instability, resolution gaps between pre-training and fine-tuning, and hunger on labelled data. Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images. Through these techniques, this paper successfully trained a 3 billion-parameter Swin Transformer V2 model, which is the largest dense vision model to date, and makes it capable of training with images of up to 1,536times1,536 resolution. It set new performance records on 4 representative vision tasks, including ImageNet-V2 image classification, COCO object detection, ADE20K semantic segmentation, and Kinetics-400 video action classification. Also note our training is much more efficient than that in Google's billion-level visual models, which consumes 40 times less labelled data and 40 times less training time. Code is available at https://github.com/microsoft/Swin-Transformer.

Two-wheelers account for a disproportionately high share of road fatalities in the Global South. Research on two-wheeler rider behavior, however, lags far behind four-wheelers, where multimodal datasets have driven major advances in Advanced Driver Assistance Systems (ADAS). To address this gap, we present the MOtorized TwO-wheeler Rider (MOTOR) dataset, the first large-scale, multi-view, multimodal resource dedicated to two-wheelers in dense, unstructured traffic. MOTOR comprises 1,629 sequences (25+ hours of video data) collected from 16 riders and integrates synchronized front, rear, and helmet videos, rider eye-gaze from wearable trackers, on-road audio, and telemetry (GPS, accelerometer, gyroscope). Rich annotations capture traffic context, rider state, 12 riding maneuvers spanning conventional and unconventional behaviors, and legality labels (Legal, Illegal, Unspecified). We benchmark rider behavior recognition and maneuver legality classification using state-of-the-art video action recognition backbones (CNN and Transformer-based), extended with multimodal fusion, and find that combining RGB, gaze, and telemetry consistently yields the best performance. MOTOR thus provides a unique foundation for advancing safety-critical understanding of two-wheeler riding. It offers the research community a benchmark to develop and evaluate models for behavior analysis, legality-aware prediction, and intelligent transportation systems. Dataset and code is available at https: //varuniiith.github.io/MOTOR-Dataset/

Video-Action Models (VAMs) have emerged as a promising framework for embodied intelligence, learning implicit world dynamics from raw video streams to produce temporally consistent action predictions. Although such models demonstrate strong performance on long-horizon tasks through visual reasoning, they remain limited in contact-rich scenarios where critical interaction states are only partially observable from vision alone. In particular, fine-grained force modulation and contact transitions are not reliably encoded in visual tokens, leading to unstable or imprecise behaviors. To bridge this gap, we introduce the Video-Tactile Action Model (VTAM), a multimodal world modeling framework that incorporates tactile perception as a complementary grounding signal. VTAM augments a pretrained video transformer with tactile streams via a lightweight modality transfer finetuning, enabling efficient cross-modal representation learning without tactile-language paired data or independent tactile pretraining. To stabilize multimodal fusion, we introduce a tactile regularization loss that enforces balanced cross-modal attention, preventing visual latent dominance in the action model. VTAM demonstrates superior performance in contact-rich manipulation, maintaining a robust success rate of 90 percent on average. In challenging scenarios such as potato chip pick-and-place requiring high-fidelity force awareness, VTAM outperforms the pi 0.5 baseline by 80 percent. Our findings demonstrate that integrating tactile feedback is essential for correcting visual estimation errors in world action models, providing a scalable approach to physically grounded embodied foundation models.

Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations. Meanwhile, large amounts of video data depicting a wide range of environments and diverse behaviors are readily available. This data provides a rich source of information about real-world dynamics and agent-environment interactions. Leveraging this data directly for imitation learning, however, has proven difficult due to the lack of action annotation required for most contemporary methods. In this work, we present Unified World Models (UWM), a framework that allows for leveraging both video and action data for policy learning. Specifically, a UWM integrates an action diffusion process and a video diffusion process within a unified transformer architecture, where independent diffusion timesteps govern each modality. We show that by simply controlling each diffusion timestep, UWM can flexibly represent a policy, a forward dynamics, an inverse dynamics, and a video generator. Through simulated and real-world experiments, we show that: (1) UWM enables effective pretraining on large-scale multitask robot datasets with both dynamics and action predictions, resulting in more generalizable and robust policies than imitation learning, (2) UWM naturally facilitates learning from action-free video data through independent control of modality-specific diffusion timesteps, further improving the performance of finetuned policies. Our results suggest that UWM offers a promising step toward harnessing large, heterogeneous datasets for scalable robot learning, and provides a simple unification between the often disparate paradigms of imitation learning and world modeling. Videos and code are available at https://weirdlabuw.github.io/uwm/.

Artificial intelligence has revolutionized the way we analyze sports videos, whether to understand the actions of games in long untrimmed videos or to anticipate the player's motion in future frames. Despite these efforts, little attention has been given to anticipating game actions before they occur. In this work, we introduce the task of action anticipation for football broadcast videos, which consists in predicting future actions in unobserved future frames, within a five- or ten-second anticipation window. To benchmark this task, we release a new dataset, namely the SoccerNet Ball Action Anticipation dataset, based on SoccerNet Ball Action Spotting. Additionally, we propose a Football Action ANticipation TRAnsformer (FAANTRA), a baseline method that adapts FUTR, a state-of-the-art action anticipation model, to predict ball-related actions. To evaluate action anticipation, we introduce new metrics, including mAP@δ, which evaluates the temporal precision of predicted future actions, as well as mAP@infty, which evaluates their occurrence within the anticipation window. We also conduct extensive ablation studies to examine the impact of various task settings, input configurations, and model architectures. Experimental results highlight both the feasibility and challenges of action anticipation in football videos, providing valuable insights into the design of predictive models for sports analytics. By forecasting actions before they unfold, our work will enable applications in automated broadcasting, tactical analysis, and player decision-making. Our dataset and code are publicly available at https://github.com/MohamadDalal/FAANTRA.

Contrastive language-image pretraining (CLIP) has significantly advanced image-based vision learning. A pressing topic subsequently arises: how can we effectively adapt CLIP to the video domain? Recent studies have focused on adjusting either the textual or visual branch of CLIP for action recognition. However, we argue that adaptations of both branches are crucial. In this paper, we propose CLAVER: a Contrastive Language-Action Video Learner, designed to shift CLIP's focus from the alignment of static visual objects and concrete nouns to the alignment of dynamic action behaviors and abstract verbs. Specifically, we introduce a novel Kronecker mask attention for temporal modeling. Our tailored Kronecker mask offers three benefits 1) it expands the temporal receptive field for each token, 2) it serves as an effective spatiotemporal heterogeneity inductive bias, mitigating the issue of spatiotemporal homogenization, and 3) it can be seamlessly plugged into transformer-based models. Regarding the textual branch, we leverage large language models to generate diverse, sentence-level and semantically rich interpretive prompts of actions, which shift the model's focus towards the verb comprehension. Extensive experiments on various benchmarks and learning scenarios demonstrate the superiority and generality of our approach.

Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present MotuBrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only, task-agnostic, and cross-embodiment robot data. Building on Motus, MotuBrain further introduces unified multiview modeling, an independent text stream for stronger language-action coupling, a shared cross-embodiment action representation, and an efficient post-training and deployment recipe for long-horizon real-world control. Our inference stack combines step reduction, compilation, FP8 quantization, DiT caching, V2A-style action-only inference, and real-time chunked closed-loop execution, achieving over 50x speedup over a naive baseline and up to 11 Hz inference. Experimentally, MotuBrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.

World Action Models (WAMs) are an emerging family of policies that tie robot action generation to future-observation modeling. In this work, we focus on the joint video--action modeling paradigm, where actions and imagined future observations are co-generated along a shared denoising or flow trajectory, so that perception, prediction, and control are coupled within one generative process. Existing WAMs typically realize this paradigm with a Mixture-of-Transformers (MoT), where video and action tokens interact through shared self-attention. This architecture can in principle assign a separate timestep t_f to each predicted latent frame, yet current systems collapse this degree of freedom onto a single shared scalar t. Under the noise-as-masking view of Diffusion Forcing, this shared schedule imposes the unjustified prior that every predicted latent is equally reliable for action generation. We instead view the per-latent schedule as a learnable information-gating policy: by changing a latent frame's noise level, the policy modulates the reliability of its Key/Value contribution to the action tokens. We propose NoiseGate, which combines independent per-latent timestep sampling during backbone training, a lightweight Gating Policy Network that emits per-latent time increments during denoising, and task-reward optimization that trains the schedule policy without hand-crafted shape priors. Built on a joint video--action MoT backbone, NoiseGate delivers consistent gains on diverse RoboTwin random-scene manipulation tasks.

Pure vision transformer architectures are highly effective for short video classification and action recognition tasks. However, due to the quadratic complexity of self attention and lack of inductive bias, transformers are resource intensive and suffer from data inefficiencies. Long form video understanding tasks amplify data and memory efficiency problems in transformers making current approaches unfeasible to implement on data or memory restricted domains. This paper introduces an efficient Spatio-Temporal Attention Network (STAN) which uses a two-stream transformer architecture to model dependencies between static image features and temporal contextual features. Our proposed approach can classify videos up to two minutes in length on a single GPU, is data efficient, and achieves SOTA performance on several long video understanding tasks.

We present COMEDIAN, a novel pipeline to initialize spatio-temporal transformers for action spotting, which involves self-supervised learning and knowledge distillation. Action spotting is a timestamp-level temporal action detection task. Our pipeline consists of three steps, with two initialization stages. First, we perform self-supervised initialization of a spatial transformer using short videos as input. Additionally, we initialize a temporal transformer that enhances the spatial transformer's outputs with global context through knowledge distillation from a pre-computed feature bank aligned with each short video segment. In the final step, we fine-tune the transformers to the action spotting task. The experiments, conducted on the SoccerNet-v2 dataset, demonstrate state-of-the-art performance and validate the effectiveness of COMEDIAN's pretraining paradigm. Our results highlight several advantages of our pretraining pipeline, including improved performance and faster convergence compared to non-pretrained models.

Autoregressive video models offer distinct advantages over bidirectional diffusion models in creating interactive video content and supporting streaming applications with arbitrary duration. In this work, we present Next-Frame Diffusion (NFD), an autoregressive diffusion transformer that incorporates block-wise causal attention, enabling iterative sampling and efficient inference via parallel token generation within each frame. Nonetheless, achieving real-time video generation remains a significant challenge for such models, primarily due to the high computational cost associated with diffusion sampling and the hardware inefficiencies inherent to autoregressive generation. To address this, we introduce two innovations: (1) We extend consistency distillation to the video domain and adapt it specifically for video models, enabling efficient inference with few sampling steps; (2) To fully leverage parallel computation, motivated by the observation that adjacent frames often share the identical action input, we propose speculative sampling. In this approach, the model generates next few frames using current action input, and discard speculatively generated frames if the input action differs. Experiments on a large-scale action-conditioned video generation benchmark demonstrate that NFD beats autoregressive baselines in terms of both visual quality and sampling efficiency. We, for the first time, achieves autoregressive video generation at over 30 Frames Per Second (FPS) on an A100 GPU using a 310M model.

Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-conditioned interactive world models. In this work, we extend rCM, an advanced diffusion distillation framework, to autoregressive video diffusion. The core philosophy of rCM lies in the complementarity between forward and reverse divergences, represented by consistency models (CMs) and distribution matching distillation (DMD), respectively, in diffusion distillation. This philosophy naturally carries over to the autoregressive setting, where teacher-forcing (TF) provides an offline, forward-divergence causal training paradigm, while self-forcing (SF) corresponds to an on-policy, reverse-divergence refinement. Our contributions are: (1) through extensive experiments, we show that teacher-forcing CM is currently the best complement to self-forcing DMD as an initialization strategy (2) we present the first implementation of teacher-forcing-based continuous-time CMs (e.g., sCM/MeanFlow) for autoregressive video diffusion, enabled by our custom-mask FlashAttention-2 JVP kernel, achieving 10times faster convergence compared to discrete-time CMs (dCMs) (3) we introduce Causal-rCM, a leading, unified, and scalable algorithm-infrastructure open recipe for diffusion distillation and causal training (4) we achieve state-of-the-art streaming video generation performance in both frame-wise and chunk-wise settings, using only synthetic data for training. Notably, our distilled 2-step causal Wan2.1-1.3B model achieves a VBench-T2V score of 84.63 with only 1 or 2 sampling steps. We further apply Causal-rCM to Cosmos 3, an advanced omnimodal world foundation model for physical AI with action-conditioned generation capability, enabling an interactive world model.

Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical world. However, existing approaches overlook the coherent and physically consistent motion representations inherently encoded across frames in VDMs. To this end, we propose Video2Act, a framework that efficiently guides robotic action learning by explicitly integrating spatial and motion-aware representations. Building on the inherent representations of VDMs, we extract foreground boundaries and inter-frame motion variations while filtering out background noise and task-irrelevant biases. These refined representations are then used as additional conditioning inputs to a diffusion transformer (DiT) action head, enabling it to reason about what to manipulate and how to move. To mitigate inference inefficiency, we propose an asynchronous dual-system design, where the VDM functions as the slow System 2 and the DiT head as the fast System 1, working collaboratively to generate adaptive actions. By providing motion-aware conditions to System 1, Video2Act maintains stable manipulation even with low-frequency updates from the VDM. For evaluation, Video2Act surpasses previous state-of-the-art VLA methods by 7.7% in simulation and 21.7% in real-world tasks in terms of average success rate, further exhibiting strong generalization capabilities.

We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully "transformerized" version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in the past been difficult to reconstruct from single images. To analyze video, we use 3D reconstructions from HMR 2.0 as input to a tracking system that operates in 3D. This enables us to deal with multiple people and maintain identities through occlusion events. Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches. Our code and models are available on the project website: https://shubham-goel.github.io/4dhumans/.

Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a Chain-of-Frames (CoF) mechanism, where reasoning is assumed to unfold sequentially across video frames. In this work, we challenge this assumption and uncover a fundamentally different mechanism. We show that reasoning in video models instead primarily emerges along the diffusion denoising steps. Through qualitative analysis and targeted probing experiments, we find that models explore multiple candidate solutions in early denoising steps and progressively converge to a final answer, a process we term Chain-of-Steps (CoS). Beyond this core mechanism, we identify several emergent reasoning behaviors critical to model performance: (1) working memory, enabling persistent reference; (2) self-correction and enhancement, allowing recovery from incorrect intermediate solutions; and (3) perception before action, where early steps establish semantic grounding and later steps perform structured manipulation. During a diffusion step, we further uncover self-evolved functional specialization within Diffusion Transformers, where early layers encode dense perceptual structure, middle layers execute reasoning, and later layers consolidate latent representations. Motivated by these insights, we present a simple training-free strategy as a proof-of-concept, demonstrating how reasoning can be improved by ensembling latent trajectories from identical models with different random seeds. Overall, our work provides a systematic understanding of how reasoning emerges in video generation models, offering a foundation to guide future research in better exploiting the inherent reasoning dynamics of video models as a new substrate for intelligence.

Generating visual instructions in a given context is essential for developing interactive world simulators. While prior works address this problem through either text-guided image manipulation or video prediction, these tasks are typically treated in isolation. This separation reveals a fundamental issue: image manipulation methods overlook how actions unfold over time, while video prediction models often ignore the intended outcomes. To this end, we propose ShowMe, a unified framework that enables both tasks by selectively activating the spatial and temporal components of video diffusion models. In addition, we introduce structure and motion consistency rewards to improve structural fidelity and temporal coherence. Notably, this unification brings dual benefits: the spatial knowledge gained through video pretraining enhances contextual consistency and realism in non-rigid image edits, while the instruction-guided manipulation stage equips the model with stronger goal-oriented reasoning for video prediction. Experiments on diverse benchmarks demonstrate that our method outperforms expert models in both instructional image and video generation, highlighting the strength of video diffusion models as a unified action-object state transformer.

This paper proposes an interaction reasoning network for modelling spatio-temporal relationships between hands and objects in video. The proposed interaction unit utilises a Transformer module to reason about each acting hand, and its spatio-temporal relation to the other hand as well as objects being interacted with. We show that modelling two-handed interactions are critical for action recognition in egocentric video, and demonstrate that by using positionally-encoded trajectories, the network can better recognise observed interactions. We evaluate our proposal on EPIC-KITCHENS and Something-Else datasets, with an ablation study.

Recognizing and comprehending human actions and gestures is a crucial perception requirement for robots to interact with humans and carry out tasks in diverse domains, including service robotics, healthcare, and manufacturing. Event cameras, with their ability to capture fast-moving objects at a high temporal resolution, offer new opportunities compared to standard action recognition in RGB videos. However, previous research on event camera action recognition has primarily focused on sensor-specific network architectures and image encoding, which may not be suitable for new sensors and limit the use of recent advancements in transformer-based architectures. In this study, we employ a computationally efficient model, namely the video transformer network (VTN), which initially acquires spatial embeddings per event-frame and then utilizes a temporal self-attention mechanism. In order to better adopt the VTN for the sparse and fine-grained nature of event data, we design Event-Contrastive Loss (L_{EC}) and event-specific augmentations. Proposed L_{EC} promotes learning fine-grained spatial cues in the spatial backbone of VTN by contrasting temporally misaligned frames. We evaluate our method on real-world action recognition of N-EPIC Kitchens dataset, and achieve state-of-the-art results on both protocols - testing in seen kitchen (74.9\% accuracy) and testing in unseen kitchens (42.43\% and 46.66\% Accuracy). Our approach also takes less computation time compared to competitive prior approaches, which demonstrates the potential of our framework EventTransAct for real-world applications of event-camera based action recognition. Project Page: https://tristandb8.github.io/EventTransAct_webpage/

Capturing interaction of hands with objects is important to autonomously detect human actions from egocentric videos. In this work, we present a pyramid video transformer with a dynamic class token generator for egocentric action recognition. Different from previous video transformers, which use the same static embedding as the class token for diverse inputs, we propose a dynamic class token generator that produces a class token for each input video by analyzing the hand-object interaction and the related motion information. The dynamic class token can diffuse such information to the entire model by communicating with other informative tokens in the subsequent transformer layers. With the dynamic class token, dissimilarity between videos can be more prominent, which helps the model distinguish various inputs. In addition, traditional video transformers explore temporal features globally, which requires large amounts of computation. However, egocentric videos often have a large amount of background scene transition, which causes discontinuities across distant frames. In this case, blindly reducing the temporal sampling rate will risk losing crucial information. Hence, we also propose a pyramid architecture to hierarchically process the video from short-term high rate to long-term low rate. With the proposed architecture, we significantly reduce the computational cost as well as the memory requirement without sacrificing from the model performance. We perform comparisons with different baseline video transformers on the EPIC-KITCHENS-100 and EGTEA Gaze+ datasets. Both quantitative and qualitative results show that the proposed model can efficiently improve the performance for egocentric action recognition.

Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts and expert collaboration, resulting in lengthy production cycles and high manpower costs. To address this issue, we automate this process with generative models, called generative video compositing. This new task strives to adaptively inject identity and motion information of foreground video to the target video in an interactive manner, allowing users to customize the size, motion trajectory, and other attributes of the dynamic elements added in final video. Specifically, we designed a novel Diffusion Transformer (DiT) pipeline based on its intrinsic properties. To maintain consistency of the target video before and after editing, we revised a light-weight DiT-based background preservation branch with masked token injection. As to inherit dynamic elements from other sources, a DiT fusion block is proposed using full self-attention, along with a simple yet effective foreground augmentation for training. Besides, for fusing background and foreground videos with different layouts based on user control, we developed a novel position embedding, named Extended Rotary Position Embedding (ERoPE). Finally, we curated a dataset comprising 61K sets of videos for our new task, called VideoComp. This data includes complete dynamic elements and high-quality target videos. Experiments demonstrate that our method effectively realizes generative video compositing, outperforming existing possible solutions in fidelity and consistency.

Video transformers have become the de facto standard for human action recognition, yet their exclusive reliance on the RGB modality still limits their adoption in certain domains. One such domain is Activities of Daily Living (ADL), where RGB alone is not sufficient to distinguish between visually similar actions, or actions observed from multiple viewpoints. To facilitate the adoption of video transformers for ADL, we hypothesize that the augmentation of RGB with human pose information, known for its sensitivity to fine-grained motion and multiple viewpoints, is essential. Consequently, we introduce the first Pose Induced Video Transformer: PI-ViT (or pi-ViT), a novel approach that augments the RGB representations learned by video transformers with 2D and 3D pose information. The key elements of pi-ViT are two plug-in modules, 2D Skeleton Induction Module and 3D Skeleton Induction Module, that are responsible for inducing 2D and 3D pose information into the RGB representations. These modules operate by performing pose-aware auxiliary tasks, a design choice that allows pi-ViT to discard the modules during inference. Notably, pi-ViT achieves the state-of-the-art performance on three prominent ADL datasets, encompassing both real-world and large-scale RGB-D datasets, without requiring poses or additional computational overhead at inference.

Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and non-visual components (e.g. action, relations) under the mutual influence of vision and language, we first propose a visual-linguistic (VL) feature. In the proposed VL feature, the scene is modeled by three modalities including (i) a global visual environment; (ii) local visual main agents; (iii) linguistic scene elements. We then introduce an autoregressive Transformer-in-Transformer (TinT) to simultaneously capture the semantic coherence of intra- and inter-event contents within a video. Finally, we present a new VL contrastive loss function to guarantee learnt embedding features are matched with the captions semantics. Comprehensive experiments and extensive ablation studies on ActivityNet Captions and YouCookII datasets show that the proposed Visual-Linguistic Transformer-in-Transform (VLTinT) outperforms prior state-of-the-art methods on accuracy and diversity. Source code is made publicly available at: https://github.com/UARK-AICV/VLTinT.

Online video understanding often relies on individual frames, leading to frame-by-frame predictions. Recent advancements such as Online Temporal Action Localization (OnTAL), extend this approach to instance-level predictions. However, existing methods mainly focus on short-term context, neglecting historical information. To address this, we introduce the History-Augmented Anchor Transformer (HAT) Framework for OnTAL. By integrating historical context, our framework enhances the synergy between long-term and short-term information, improving the quality of anchor features crucial for classification and localization. We evaluate our model on both procedural egocentric (PREGO) datasets (EGTEA and EPIC) and standard non-PREGO OnTAL datasets (THUMOS and MUSES). Results show that our model outperforms state-of-the-art approaches significantly on PREGO datasets and achieves comparable or slightly superior performance on non-PREGO datasets, underscoring the importance of leveraging long-term history, especially in procedural and egocentric action scenarios. Code is available at: https://github.com/sakibreza/ECCV24-HAT/

Badminton, known for having the fastest ball speeds among all sports, presents significant challenges to the field of computer vision, including player identification, court line detection, shuttlecock trajectory tracking, and player stroke-type classification. In this paper, we introduce a novel video clipping strategy to extract frames of each player's racket swing in a badminton broadcast match. These clipped frames are then processed by three existing models: one for Human Pose Estimation to obtain human skeletal joints, another for shuttlecock trajectory tracking, and the other for court line detection to determine player positions on the court. Leveraging these data as inputs, we propose Badminton Stroke-type Transformer (BST) to classify player stroke-types in singles. To the best of our knowledge, experimental results demonstrate that our method outperforms the previous state-of-the-art on the largest publicly available badminton video dataset (ShuttleSet), another badminton dataset (BadmintonDB), and a tennis dataset (TenniSet). These results suggest that effectively leveraging ball trajectory is a promising direction for action recognition in racket sports.

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. The locality of the proposed video architecture is realized by adapting the Swin Transformer designed for the image domain, while continuing to leverage the power of pre-trained image models. Our approach achieves state-of-the-art accuracy on a broad range of video recognition benchmarks, including on action recognition (84.9 top-1 accuracy on Kinetics-400 and 86.1 top-1 accuracy on Kinetics-600 with ~20x less pre-training data and ~3x smaller model size) and temporal modeling (69.6 top-1 accuracy on Something-Something v2). The code and models will be made publicly available at https://github.com/SwinTransformer/Video-Swin-Transformer.

Online temporal action localization (On-TAL) is the task of identifying multiple action instances given a streaming video. Since existing methods take as input only a video segment of fixed size per iteration, they are limited in considering long-term context and require tuning the segment size carefully. To overcome these limitations, we propose memory-augmented transformer (MATR). MATR utilizes the memory queue that selectively preserves the past segment features, allowing to leverage long-term context for inference. We also propose a novel action localization method that observes the current input segment to predict the end time of the ongoing action and accesses the memory queue to estimate the start time of the action. Our method outperformed existing methods on two datasets, THUMOS14 and MUSES, surpassing not only TAL methods in the online setting but also some offline TAL methods.

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition models against common distribution shifts has so far not been demonstrated. We propose to address this problem with an approach tailored to spatio-temporal models that is capable of adaptation on a single video sample at a step. It consists in a feature distribution alignment technique that aligns online estimates of test set statistics towards the training statistics. We further enforce prediction consistency over temporally augmented views of the same test video sample. Evaluations on three benchmark action recognition datasets show that our proposed technique is architecture-agnostic and able to significantly boost the performance on both, the state of the art convolutional architecture TANet and the Video Swin Transformer. Our proposed method demonstrates a substantial performance gain over existing test-time adaptation approaches in both evaluations of a single distribution shift and the challenging case of random distribution shifts. Code will be available at https://github.com/wlin-at/ViTTA.

We present Action Agent, a two-stage framework that unifies agentic navigation video generation with flow-constrained diffusion control for multi-embodiment robot navigation. In Stage I, a large language model (LLM) acts as an orchestration module that selects video diffusion models, refines prompts through iterative validation, and accumulates cross-task memory to synthesize physically plausible first-person navigation videos from language and image inputs. This increases video generation success from 35% (single-shot) to 86% across 50 navigation tasks. In Stage II, we introduce FlowDiT, a Flow-Constrained Diffusion Transformer that converts optimized goal videos and language instructions into continuous velocity commands using action-space denoising diffusion. FlowDiT integrates DINOv2 visual features, learned optical flow for ego-motion representation, and CLIP language embeddings for semantic stopping. We pretrain on the RECON outdoor navigation dataset and fine-tune on 203 Unitree G1 humanoid episodes collected in Isaac Sim to calibrate velocity dynamics. A single 43M-parameter checkpoint achieves 73.2% navigation success in simulation and 64.7% task completion on a real Unitree G1 in unseen indoor environments under open-loop execution, while operating at 40--47 Hz. We evaluate Action Agent across three embodiments: a Unitree G1 humanoid (real hardware), a drone, and a wheeled mobile robot (Isaac Sim), demonstrating that decoupling trajectory imagination from execution yields a scalable and embodiment-aware paradigm for language-guided navigation.

This paper focuses on building object-centric representations for long-term action anticipation in videos. Our key motivation is that objects provide important cues to recognize and predict human-object interactions, especially when the predictions are longer term, as an observed "background" object could be used by the human actor in the future. We observe that existing object-based video recognition frameworks either assume the existence of in-domain supervised object detectors or follow a fully weakly-supervised pipeline to infer object locations from action labels. We propose to build object-centric video representations by leveraging visual-language pretrained models. This is achieved by "object prompts", an approach to extract task-specific object-centric representations from general-purpose pretrained models without finetuning. To recognize and predict human-object interactions, we use a Transformer-based neural architecture which allows the "retrieval" of relevant objects for action anticipation at various time scales. We conduct extensive evaluations on the Ego4D, 50Salads, and EGTEA Gaze+ benchmarks. Both quantitative and qualitative results confirm the effectiveness of our proposed method.

This work introduces Video Diffusion Transformer (VDT), which pioneers the use of transformers in diffusion-based video generation. It features transformer blocks with modularized temporal and spatial attention modules to leverage the rich spatial-temporal representation inherited in transformers. We also propose a unified spatial-temporal mask modeling mechanism, seamlessly integrated with the model, to cater to diverse video generation scenarios. VDT offers several appealing benefits. 1) It excels at capturing temporal dependencies to produce temporally consistent video frames and even simulate the physics and dynamics of 3D objects over time. 2) It facilitates flexible conditioning information, \eg, simple concatenation in the token space, effectively unifying different token lengths and modalities. 3) Pairing with our proposed spatial-temporal mask modeling mechanism, it becomes a general-purpose video diffuser for harnessing a range of tasks, including unconditional generation, video prediction, interpolation, animation, and completion, etc. Extensive experiments on these tasks spanning various scenarios, including autonomous driving, natural weather, human action, and physics-based simulation, demonstrate the effectiveness of VDT. Additionally, we present comprehensive studies on how \model handles conditioning information with the mask modeling mechanism, which we believe will benefit future research and advance the field. Project page: https:VDT-2023.github.io

We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework, addressing the critical limitations of prior unified world models (e.g., UWM) that only model 2D pixel-space and fail to balance action efficiency and world modeling quality. To leverage the strong visual priors of pretrained video diffusion models, X-WAM imagines the future world by predicting multi-view RGB-D videos, and obtains spatial information efficiently through a lightweight structural adaptation: replicating the final few blocks of the pretrained Diffusion Transformer into a dedicated depth prediction branch for the reconstruction of future spatial information. Moreover, we propose Asynchronous Noise Sampling (ANS) to jointly optimize generation quality and action decoding efficiency. ANS applies a specialized asynchronous denoising schedule during inference, which rapidly decodes actions with fewer steps to enable efficient real-time execution, while dedicating the full sequence of steps to generate high-fidelity video. Rather than entirely decoupling the timesteps during training, ANS samples from their joint distribution to align with the inference distribution. Pretrained on over 5,800 hours of robotic data, X-WAM achieves 79.2% and 90.7% average success rate on RoboCasa and RoboTwin 2.0 benchmarks, while producing high-fidelity 4D reconstruction and generation surpassing existing methods in both visual and geometric metrics.

This paper introduces ViNet-S, a 36MB model based on the ViNet architecture with a U-Net design, featuring a lightweight decoder that significantly reduces model size and parameters without compromising performance. Additionally, ViNet-A (148MB) incorporates spatio-temporal action localization (STAL) features, differing from traditional video saliency models that use action classification backbones. Our studies show that an ensemble of ViNet-S and ViNet-A, by averaging predicted saliency maps, achieves state-of-the-art performance on three visual-only and six audio-visual saliency datasets, outperforming transformer-based models in both parameter efficiency and real-time performance, with ViNet-S reaching over 1000fps.

Counting repetitive actions are widely seen in human activities such as physical exercise. Existing methods focus on performing repetitive action counting in short videos, which is tough for dealing with longer videos in more realistic scenarios. In the data-driven era, the degradation of such generalization capability is mainly attributed to the lack of long video datasets. To complement this margin, we introduce a new large-scale repetitive action counting dataset covering a wide variety of video lengths, along with more realistic situations where action interruption or action inconsistencies occur in the video. Besides, we also provide a fine-grained annotation of the action cycles instead of just counting annotation along with a numerical value. Such a dataset contains 1,451 videos with about 20,000 annotations, which is more challenging. For repetitive action counting towards more realistic scenarios, we further propose encoding multi-scale temporal correlation with transformers that can take into account both performance and efficiency. Furthermore, with the help of fine-grained annotation of action cycles, we propose a density map regression-based method to predict the action period, which yields better performance with sufficient interpretability. Our proposed method outperforms state-of-the-art methods on all datasets and also achieves better performance on the unseen dataset without fine-tuning. The dataset and code are available.

Human object interaction (HOI), gaze pattern, and their anticipation are intricately linked, providing valuable insights into cognitive processes, intentions, and behavior. However, most existing models handle gaze and actions separately, missing both their interdependence and the advantages of a unified solution. This paper presents a novel unified framework, SAGE (Synchronized Action-GazE), which integrates simultaneous recognition and anticipation of both HOI and human gaze into a single unified end-to-end trainable model. Our approach leverages a transformer-based architecture and incorporates gaze data into spatiotemporal attention mechanisms to simultaneously predict current and future human actions and gaze behavior. We explore this bidirectional relationship between gaze and actions under different scenarios, whether requiring a close-up, detailed view (egocentric) or a wider, more contextual view (exocentric), making our framework versatile for various applications. Additionally, due to lack of datasets for comprehensive analysis of both HOI and gaze in exocentric videos, we establish a new benchmark Exo-Cook to facilitate further research in this domain. Experiments on three benchmark datasets: VidHOI, EGTEA Gaze+, and Exo-Cook show that jointly modeling gaze and actions across current and future frames achieves consistently strong results, often surpassing specialized state-of-the-art models tailored to individual tasks. By unifying actions and attention in a comprehensive way, our work lays the groundwork for more intuitive human-machine interaction.

Modeling long-term context in videos is crucial for many fine-grained tasks including temporal action segmentation. An interesting question that is still open is how much long-term temporal context is needed for optimal performance. While transformers can model the long-term context of a video, this becomes computationally prohibitive for long videos. Recent works on temporal action segmentation thus combine temporal convolutional networks with self-attentions that are computed only for a local temporal window. While these approaches show good results, their performance is limited by their inability to capture the full context of a video. In this work, we try to answer how much long-term temporal context is required for temporal action segmentation by introducing a transformer-based model that leverages sparse attention to capture the full context of a video. We compare our model with the current state of the art on three datasets for temporal action segmentation, namely 50Salads, Breakfast, and Assembly101. Our experiments show that modeling the full context of a video is necessary to obtain the best performance for temporal action segmentation.

Generalization in robot manipulation is essential for deploying robots in open-world environments and advancing toward artificial general intelligence. While recent Vision-Language-Action (VLA) models leverage large pre-trained understanding models for perception and instruction following, their ability to generalize to novel tasks, objects, and settings remains limited. In this work, we present VideoVLA, a simple approach that explores the potential of transforming large video generation models into robotic VLA manipulators. Given a language instruction and an image, VideoVLA predicts an action sequence as well as the future visual outcomes. Built on a multi-modal Diffusion Transformer, VideoVLA jointly models video, language, and action modalities, using pre-trained video generative models for joint visual and action forecasting. Our experiments show that high-quality imagined futures correlate with reliable action predictions and task success, highlighting the importance of visual imagination in manipulation. VideoVLA demonstrates strong generalization, including imitating other embodiments' skills and handling novel objects. This dual-prediction strategy - forecasting both actions and their visual consequences - explores a paradigm shift in robot learning and unlocks generalization capabilities in manipulation systems.

Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer networks for temporal action localization in videos. To this end, we present ActionFormer -- a simple yet powerful model to identify actions in time and recognize their categories in a single shot, without using action proposals or relying on pre-defined anchor windows. ActionFormer combines a multiscale feature representation with local self-attention, and uses a light-weighted decoder to classify every moment in time and estimate the corresponding action boundaries. We show that this orchestrated design results in major improvements upon prior works. Without bells and whistles, ActionFormer achieves 71.0% mAP at tIoU=0.5 on THUMOS14, outperforming the best prior model by 14.1 absolute percentage points. Further, ActionFormer demonstrates strong results on ActivityNet 1.3 (36.6% average mAP) and EPIC-Kitchens 100 (+13.5% average mAP over prior works). Our code is available at http://github.com/happyharrycn/actionformer_release.

Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy frequently comes with high computational costs. This is a particular issue in video recognition, where models are often applied repeatedly across frames or temporal chunks. In this work, we exploit temporal redundancy between subsequent inputs to reduce the cost of Transformers for video processing. We describe a method for identifying and re-processing only those tokens that have changed significantly over time. Our proposed family of models, Eventful Transformers, can be converted from existing Transformers (often without any re-training) and give adaptive control over the compute cost at runtime. We evaluate our method on large-scale datasets for video object detection (ImageNet VID) and action recognition (EPIC-Kitchens 100). Our approach leads to significant computational savings (on the order of 2-4x) with only minor reductions in accuracy.

Recent progress in robotic world models has leveraged video diffusion transformers to predict future observations conditioned on historical states and actions. While these models can simulate realistic visual outcomes, they often exhibit poor action-following precision, hindering their utility for downstream robotic learning. In this work, we introduce World-VLA-Loop, a closed-loop framework for the joint refinement of world models and Vision-Language-Action (VLA) policies. We propose a state-aware video world model that functions as a high-fidelity interactive simulator by jointly predicting future observations and reward signals. To enhance reliability, we introduce the SANS dataset, which incorporates near-success trajectories to improve action-outcome alignment within the world model. This framework enables a closed-loop for reinforcement learning (RL) post-training of VLA policies entirely within a virtual environment. Crucially, our approach facilitates a co-evolving cycle: failure rollouts generated by the VLA policy are iteratively fed back to refine the world model precision, which in turn enhances subsequent RL optimization. Evaluations across simulation and real-world tasks demonstrate that our framework significantly boosts VLA performance with minimal physical interaction, establishing a mutually beneficial relationship between world modeling and policy learning for general-purpose robotics. Project page: https://showlab.github.io/World-VLA-Loop/.

Pretrained video generation models provide strong priors for robot control, but existing unified world action models still struggle to decode reliable actions without substantial robot-specific training. We attribute this limitation to a structural mismatch: while video models capture how scenes evolve, action generation requires explicit reasoning about where to interact and the underlying manipulation intent. We introduce AIM, an intent-aware unified world action model that bridges this gap via an explicit spatial interface. Instead of decoding actions directly from future visual representations, AIM predicts an aligned spatial value map that encodes task-relevant interaction structure, enabling a control-oriented abstraction of future dynamics. Built on a pretrained video generation model, AIM jointly models future observations and value maps within a shared mixture-of-transformers architecture. It employs intent-causal attention to route future information to the action branch exclusively through the value representation. We further propose a self-distillation reinforcement learning stage that freezes the video and value branches and optimizes only the action head using dense rewards derived from projected value-map responses together with sparse task-level signals. To support training and evaluation, we construct a simulation dataset of 30K manipulation trajectories with synchronized multi-view observations, actions, and value-map annotations. Experiments on RoboTwin 2.0 benchmark show that AIM achieves a 94.0% average success rate, significantly outperforming prior unified world action baselines. Notably, the improvement is more pronounced in long-horizon and contact-sensitive manipulation tasks, demonstrating the effectiveness of explicit spatial-intent modeling as a bridge between visual world modeling and robot control.

Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the vision transformer (ViT) exclusively for unimodal perception tasks such as action recognition and object segmentation, without adapting to downstream vision-language tasks; or (2) only within the LLM while leaving the ViT output intact, often requiring complex text-conditioned token selection mechanisms. In this paper, we introduce Spatio-Temporal Token Scoring (STTS), a simple and lightweight module that prunes vision tokens across both the ViT and the LLM without text conditioning or token merging, and is fully compatible with end-to-end training. By learning how to score temporally via an auxiliary loss and spatially via LLM downstream gradients, aided by our efficient packing algorithm, STTS prunes 50% of vision tokens throughout the entire architecture, resulting in a 62% improvement in efficiency during both training and inference with only a 0.7% drop in average performance across 13 short and long video QA tasks. Efficiency gains increase with more sampled frames per video. Applying test-time scaling for long-video QA further yields performance gains of 0.5-1% compared to the baseline. Overall, STTS represents a novel, simple yet effective technique for unified, architecture-wide vision token pruning.

Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often generate clips based on static prompts (e.g., text or images), limiting their ability to model interactive and dynamic scenarios. In this paper, we propose Dynamic World Simulation (DWS), a novel approach to transform pre-trained video generative models into controllable world simulators capable of executing specified action trajectories. To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module that seamlessly integrates into any existing model. Instead of focusing on complex visual details, we demonstrate that consistent dynamic transition modeling is the key to building powerful world simulators. Building upon this insight, we further introduce a motion-reinforced loss that enhances action controllability by compelling the model to capture dynamic changes more effectively. Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models, achieving significant improvements in generating action-controllable, dynamically consistent videos across games and robotics domains. Moreover, to facilitate the applications of the learned world simulator in downstream tasks such as model-based reinforcement learning, we propose prioritized imagination to improve sample efficiency, demonstrating competitive performance compared with state-of-the-art methods.

Human perception of surroundings is often guided by the various poses present within the environment. Many computer vision tasks, such as human action recognition and robot imitation learning, rely on pose-based entities like human skeletons or robotic arms. However, conventional Vision Transformer (ViT) models uniformly process all patches, neglecting valuable pose priors in input videos. We argue that incorporating poses into RGB data is advantageous for learning fine-grained and viewpoint-agnostic representations. Consequently, we introduce two strategies for learning pose-aware representations in ViTs. The first method, called Pose-aware Attention Block (PAAB), is a plug-and-play ViT block that performs localized attention on pose regions within videos. The second method, dubbed Pose-Aware Auxiliary Task (PAAT), presents an auxiliary pose prediction task optimized jointly with the primary ViT task. Although their functionalities differ, both methods succeed in learning pose-aware representations, enhancing performance in multiple diverse downstream tasks. Our experiments, conducted across seven datasets, reveal the efficacy of both pose-aware methods on three video analysis tasks, with PAAT holding a slight edge over PAAB. Both PAAT and PAAB surpass their respective backbone Transformers by up to 9.8% in real-world action recognition and 21.8% in multi-view robotic video alignment. Code is available at https://github.com/dominickrei/PoseAwareVT.

Sequential video understanding, as an emerging video understanding task, has driven lots of researchers' attention because of its goal-oriented nature. This paper studies weakly supervised sequential video understanding where the accurate time-stamp level text-video alignment is not provided. We solve this task by borrowing ideas from CLIP. Specifically, we use a transformer to aggregate frame-level features for video representation and use a pre-trained text encoder to encode the texts corresponding to each action and the whole video, respectively. To model the correspondence between text and video, we propose a multiple granularity loss, where the video-paragraph contrastive loss enforces matching between the whole video and the complete script, and a fine-grained frame-sentence contrastive loss enforces the matching between each action and its description. As the frame-sentence correspondence is not available, we propose to use the fact that video actions happen sequentially in the temporal domain to generate pseudo frame-sentence correspondence and supervise the network training with the pseudo labels. Extensive experiments on video sequence verification and text-to-video matching show that our method outperforms baselines by a large margin, which validates the effectiveness of our proposed approach. Code is available at https://github.com/svip-lab/WeakSVR

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Second, they are vulnerable to practical attacking scenarios where attackers probe for privacy from an entire video rather than individual frames. To address these issues, we propose a novel framework STPrivacy to perform video-level PPAR. For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i.e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective. In specific, our privacy sparsification mechanism applies adaptive token selection to abandon action-irrelevant tubelets. Then, our anonymization mechanism implicitly manipulates the remaining action-tubelets to erase privacy in the embedding space through adversarial learning. These mechanisms provide significant advantages in terms of privacy preservation for human eyes and action-privacy trade-off adjustment during deployment. We additionally contribute the first two large-scale PPAR benchmarks, VP-HMDB51 and VP-UCF101, to the community. Extensive evaluations on them, as well as two other tasks, validate the effectiveness and generalization capability of our framework.

Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant strides in maintaining temporal consistency, they are predominantly confined to non-interactive scenarios where models merely showcase garments. This limitation overlooks a crucial aspect of real-world apparel presentation: active human-garment interaction. To bridge this gap, we introduce and formalize a new challenging task: Interactive Video Virtual Try-On (Interactive VVT), where subjects in the video actively engage with their clothing. This task introduces unique challenges beyond simple texture preservation, including: (1) resolving the semantic ambiguity of interactions from standard pose information, and (2) learning complex garment deformations from video where interactive moments are sparse and brief. To address these challenges, we propose iTryOn, a novel framework built upon a large-scale video diffusion Transformer. iTryOn pioneers a multi-level interaction injection mechanism to guide the generation of complex dynamics. At the spatial level, we introduce a garment-agnostic 3D hand prior to provide fine-grained guidance for precise hand-garment contact, effectively resolving spatial ambiguity. At the semantic level, iTryOn leverages global captions for overall context and time-stamped action captions for localized interactions, synchronized via our novel Action-aware Rotational Position Embedding (A-RoPE). Extensive experiments demonstrate that iTryOn not only achieves state-of-the-art performance on traditional VVT benchmarks but also establishes a commanding lead in the new interactive setting, marking a significant step towards more dynamic and controllable virtual try-on experiences.

Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background video, human trajectory and action patterns. In this paper, we propose a decomposed human motion control and video generation framework that explicitly decouples motion from appearance, subject from background, and action from trajectory, enabling flexible mix-and-match composition of these elements. Concretely, we first build a ground-aware 3D world coordinate system and perform motion editing directly in the 3D space. Trajectory control is implemented by unprojecting edited 2D trajectories into 3D with focal-length calibration and coordinate transformation, followed by speed alignment and orientation adjustment; actions are supplied by a motion bank or generated via text-to-motion methods. Then, based on modern text-to-video diffusion transformer models, we inject the subject as tokens for full attention, concatenate the background along the channel dimension, and add motion (trajectory and action) control signals by addition. Such a design opens up the possibility for us to generate realistic videos of anyone doing anything anywhere. Extensive experiments on benchmark datasets and real-world cases demonstrate that our method achieves state-of-the-art performance on both element-wise controllability and overall video quality.

In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the temporal context, we propose a transformer-based multimodal model that ingests video and audio as input modalities, with an explicit language model providing action sequence context to enhance the predictions. We test our approach on EPIC-KITCHENS and EGTEA datasets reporting state-of-the-art performance. Our ablations showcase the advantage of utilising temporal context as well as incorporating audio input modality and language model to rescore predictions. Code and models at: https://github.com/ekazakos/MTCN.

Scaling robot learning requires massive, diverse trajectory data, yet collection is currently bottlenecked by physical teleoperation, where every demonstration binds operator time to specific hardware and workspaces. We introduce digital teleoperation, a paradigm that decouples data collection from physical constraints by replacing the real robot with a generative world model. In this framework, an operator's hand-pose stream drives a robot-centric generative world model to synthesize high-fidelity egocentric videos from a single reference image. The recorded pose stream serves as an embodiment-agnostic action label transferable to any target robot via standard retargeting, yielding complete state-action trajectories for imitation learning independent of physical hardware. We instantiate this paradigm in RynnWorld-Teleop, a system that integrates depth-aware skeletal conditioning, progressive human-to-robot training on a video Diffusion Transformer, and streaming autoregressive distillation. This pipeline compresses the generative process into a single-pass inference, enabling 40+ FPS, real-time interactive generation on a single H100 GPU. Policies trained exclusively on RynnWorld-Teleop-generated data achieve effective zero-shot Sim2Real transfer across dexterous and diverse bimanual tasks. Moreover, augmenting real-world datasets with our digitally teleoperated data consistently improves success rates, demonstrating that RynnWorld-Teleop serves as a high-fidelity, scalable data engine for the next generation of robotic agents.

We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts physically grounded future visual trajectories from current observations across robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer. This unified formulation provides three promising application directions: synthetic data generation for policy training augmentation, scalable virtual environments for policy evaluation, and language-guided planning signals for downstream robot control. This is achieved through a three-part design: a) Double-Stream MMDiT with MLLM Action Encoding, where a 60-layer double-stream diffusion transformer couples frozen Qwen2.5-VL semantics with video-VAE latents through layer-wise joint attention; b) Embodied World Knowledge (EWK), an 8.6M video-text corpus (200M+ frames) with action-language mapping over 20+ embodiments and 500+ action categories; and c) General+Expert Progressive Curriculum, a two-stage training strategy that first learns general visual priors and then injects embodied specialization under a shared language interface. Extensive results show strong competitiveness: ranks 1st overall on EWMBench and DreamGen Bench, outperforms all open-source models on WorldModelBench and PBench. Additional zero-shot analyses on RoboTwin-IF benchmark further support robust generalization and multi-view consistency.

Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modalities of audio and video exhibit different temporal extents of events and distinct labels. We address the interplay between the two modalities in long videos by explicitly modelling the temporal extents of audio and visual events. We propose the Time Interval Machine (TIM) where a modality-specific time interval poses as a query to a transformer encoder that ingests a long video input. The encoder then attends to the specified interval, as well as the surrounding context in both modalities, in order to recognise the ongoing action. We test TIM on three long audio-visual video datasets: EPIC-KITCHENS, Perception Test, and AVE, reporting state-of-the-art (SOTA) for recognition. On EPIC-KITCHENS, we beat previous SOTA that utilises LLMs and significantly larger pre-training by 2.9% top-1 action recognition accuracy. Additionally, we show that TIM can be adapted for action detection, using dense multi-scale interval queries, outperforming SOTA on EPIC-KITCHENS-100 for most metrics, and showing strong performance on the Perception Test. Our ablations show the critical role of integrating the two modalities and modelling their time intervals in achieving this performance. Code and models at: https://github.com/JacobChalk/TIM

In this paper, we address the challenges posed by the substantial training time and memory consumption associated with video transformers, focusing on the ViViT (Video Vision Transformer) model, in particular the Factorised Encoder version, as our baseline for action recognition tasks. The factorised encoder variant follows the late-fusion approach that is adopted by many state of the art approaches. Despite standing out for its favorable speed/accuracy tradeoffs among the different variants of ViViT, its considerable training time and memory requirements still pose a significant barrier to entry. Our method is designed to lower this barrier and is based on the idea of freezing the spatial transformer during training. This leads to a low accuracy model if naively done. But we show that by (1) appropriately initializing the temporal transformer (a module responsible for processing temporal information) (2) introducing a compact adapter model connecting frozen spatial representations ((a module that selectively focuses on regions of the input image) to the temporal transformer, we can enjoy the benefits of freezing the spatial transformer without sacrificing accuracy. Through extensive experimentation over 6 benchmarks, we demonstrate that our proposed training strategy significantly reduces training costs (by sim 50%) and memory consumption while maintaining or slightly improving performance by up to 1.79\% compared to the baseline model. Our approach additionally unlocks the capability to utilize larger image transformer models as our spatial transformer and access more frames with the same memory consumption.

Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and long-horizon 3D consistency. Most prior works treat user actions as abstract conditioning signals, overlooking the fundamental geometric coupling between actions and the 3D world, whereby actions induce relative camera motions that accumulate into a global camera pose within a 3D world. In this paper, we establish camera pose as a unifying geometric representation to jointly ground immediate action control and long-term 3D consistency. First, we define a physics-based continuous action space and represent user inputs in the Lie algebra to derive precise 6-DoF camera poses, which are injected into the generative model via a camera embedder to ensure accurate action alignment. Second, we use global camera poses as spatial indices to retrieve relevant past observations, enabling geometrically consistent revisiting of locations during long-horizon navigation. To support this research, we introduce a large-scale dataset comprising 3,000 minutes of authentic human gameplay annotated with camera trajectories and textual descriptions. Extensive experiments show that our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency.

Interactive world models for first-person shooter (FPS) games must resolve high-frequency overlapping control signals at every frame without disrupting unaffected regions. Existing methods inject actions globally and train on single titles, failing under dense FPS inputs. We observe that FPS actions are spatially selective: discrete events such as firing or reloading affect only a localized region around the weapon (the scope), while continuous camera and movement signals govern stable surroundings. We propose SCOPE, which inserts a conditioning module into each transformer block of a pretrained video diffusion model. It reshapes features into per-pixel temporal sequences so that each position computes its action response from local visual content. This separates in-scope effects from out-of-scope generation without segmentation labels. We also introduce CrossFPS, the first multi-game FPS dataset with frame-aligned action telemetry. It comprises 69K clips from 7 titles with 10-DoF controller signals, curated to remove gameplay bias. The model learns general visual-to-action mappings rather than game-specific patterns, enabling zero-shot transfer to unseen scenes. Experiments confirm strong action responsiveness, precise scope separation, and effective cross-game generalization.

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI -- effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 https://openmdw.ai/license/1-1/ License at https://github.com/nvidia/cosmos}{github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3 . The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3 .

Multi-modal multi-view action recognition is a rapidly growing field in computer vision, offering significant potential for applications in surveillance. However, current datasets often fail to address real-world challenges such as wide-area distributed settings, asynchronous data streams, and the lack of frame-level annotations. Furthermore, existing methods face difficulties in effectively modeling inter-view relationships and enhancing spatial feature learning. In this paper, we introduce the MultiSensor-Home dataset, a novel benchmark designed for comprehensive action recognition in home environments, and also propose the Multi-modal Multi-view Transformer-based Sensor Fusion (MultiTSF) method. The proposed MultiSensor-Home dataset features untrimmed videos captured by distributed sensors, providing high-resolution RGB and audio data along with detailed multi-view frame-level action labels. The proposed MultiTSF method leverages a Transformer-based fusion mechanism to dynamically model inter-view relationships. Furthermore, the proposed method integrates a human detection module to enhance spatial feature learning, guiding the model to prioritize frames with human activity to enhance action the recognition accuracy. Experiments on the proposed MultiSensor-Home and the existing MM-Office datasets demonstrate the superiority of MultiTSF over the state-of-the-art methods. Quantitative and qualitative results highlight the effectiveness of the proposed method in advancing real-world multi-modal multi-view action recognition. The source code is available at https://github.com/thanhhff/MultiTSF.

We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of transformer layers. In order to handle the long sequences of tokens encountered in video, we propose several, efficient variants of our model which factorise the spatial- and temporal-dimensions of the input. Although transformer-based models are known to only be effective when large training datasets are available, we show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple video classification benchmarks including Kinetics 400 and 600, Epic Kitchens, Something-Something v2 and Moments in Time, outperforming prior methods based on deep 3D convolutional networks. To facilitate further research, we release code at https://github.com/google-research/scenic/tree/main/scenic/projects/vivit

The present few-shot temporal action localization model can't handle the situation where videos contain multiple action instances. So the purpose of this paper is to achieve manifold action instances localization in a lengthy untrimmed query video using limited trimmed support videos. To address this challenging problem effectively, we proposed a novel solution involving a spatial-channel relation transformer with probability learning and cluster refinement. This method can accurately identify the start and end boundaries of actions in the query video, utilizing only a limited number of labeled videos. Our proposed method is adept at capturing both temporal and spatial contexts to effectively classify and precisely locate actions in videos, enabling a more comprehensive utilization of these crucial details. The selective cosine penalization algorithm is designed to suppress temporal boundaries that do not include action scene switches. The probability learning combined with the label generation algorithm alleviates the problem of action duration diversity and enhances the model's ability to handle fuzzy action boundaries. The interval cluster can help us get the final results with multiple instances situations in few-shot temporal action localization. Our model achieves competitive performance through meticulous experimentation utilizing the benchmark datasets ActivityNet1.3 and THUMOS14. Our code is readily available at https://github.com/ycwfs/FMI-TAL.

We train models to Predict Ego-centric Video from human Actions (PEVA), given the past video and an action represented by the relative 3D body pose. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, our model learns to simulate how physical human actions shape the environment from a first-person point of view. We train an auto-regressive conditional diffusion transformer on Nymeria, a large-scale dataset of real-world egocentric video and body pose capture. We further design a hierarchical evaluation protocol with increasingly challenging tasks, enabling a comprehensive analysis of the model's embodied prediction and control abilities. Our work represents an initial attempt to tackle the challenges of modeling complex real-world environments and embodied agent behaviors with video prediction from the perspective of a human.

This paper presents the Holistic and Multi-Granular Surgical Scene Understanding of Prostatectomies (GraSP) dataset, a curated benchmark that models surgical scene understanding as a hierarchy of complementary tasks with varying levels of granularity. Our approach encompasses long-term tasks, such as surgical phase and step recognition, and short-term tasks, including surgical instrument segmentation and atomic visual actions detection. To exploit our proposed benchmark, we introduce the Transformers for Actions, Phases, Steps, and Instrument Segmentation (TAPIS) model, a general architecture that combines a global video feature extractor with localized region proposals from an instrument segmentation model to tackle the multi-granularity of our benchmark. Through extensive experimentation in ours and alternative benchmarks, we demonstrate TAPIS's versatility and state-of-the-art performance across different tasks. This work represents a foundational step forward in Endoscopic Vision, offering a novel framework for future research towards holistic surgical scene understanding.

This paper presents EasyAnimate, an advanced method for video generation that leverages the power of transformer architecture for high-performance outcomes. We have expanded the DiT framework originally designed for 2D image synthesis to accommodate the complexities of 3D video generation by incorporating a motion module block. It is used to capture temporal dynamics, thereby ensuring the production of consistent frames and seamless motion transitions. The motion module can be adapted to various DiT baseline methods to generate video with different styles. It can also generate videos with different frame rates and resolutions during both training and inference phases, suitable for both images and videos. Moreover, we introduce slice VAE, a novel approach to condense the temporal axis, facilitating the generation of long duration videos. Currently, EasyAnimate exhibits the proficiency to generate videos with 144 frames. We provide a holistic ecosystem for video production based on DiT, encompassing aspects such as data pre-processing, VAE training, DiT models training (both the baseline model and LoRA model), and end-to-end video inference. Code is available at: https://github.com/aigc-apps/EasyAnimate. We are continuously working to enhance the performance of our method.

Video frame interpolation has been actively studied with the development of convolutional neural networks. However, due to the intrinsic limitations of kernel weight sharing in convolution, the interpolated frame generated by it may lose details. In contrast, the attention mechanism in Transformer can better distinguish the contribution of each pixel, and it can also capture long-range pixel dependencies, which provides great potential for video interpolation. Nevertheless, the original Transformer is commonly used for 2D images; how to develop a Transformer-based framework with consideration of temporal self-attention for video frame interpolation remains an open issue. In this paper, we propose Video Frame Interpolation Flow Transformer to incorporate motion dynamics from optical flows into the self-attention mechanism. Specifically, we design a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making our framework suitable for interpolating frames with large motion while maintaining reasonably low complexity. In addition, we construct a multi-scale architecture to account for multi-scale motion, further improving the overall performance. Extensive experiments on three benchmarks demonstrate that the proposed method can generate interpolated frames with better visual quality than state-of-the-art methods.

Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations among elements in sequential data. However, there are several major concerns when directly applying the Transformer to the action segmentation task, such as the lack of inductive biases with small training sets, the deficit in processing long input sequence, and the limitation of the decoder architecture to utilize temporal relations among multiple action segments to refine the initial predictions. To address these concerns, we design an efficient Transformer-based model for action segmentation task, named ASFormer, with three distinctive characteristics: (i) We explicitly bring in the local connectivity inductive priors because of the high locality of features. It constrains the hypothesis space within a reliable scope, and is beneficial for the action segmentation task to learn a proper target function with small training sets. (ii) We apply a pre-defined hierarchical representation pattern that efficiently handles long input sequences. (iii) We carefully design the decoder to refine the initial predictions from the encoder. Extensive experiments on three public datasets demonstrate that effectiveness of our methods. Code is available at https://github.com/ChinaYi/ASFormer.

We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches. Our experimental study compares different self-attention schemes and suggests that "divided attention," where temporal attention and spatial attention are separately applied within each block, leads to the best video classification accuracy among the design choices considered. Despite the radically new design, TimeSformer achieves state-of-the-art results on several action recognition benchmarks, including the best reported accuracy on Kinetics-400 and Kinetics-600. Finally, compared to 3D convolutional networks, our model is faster to train, it can achieve dramatically higher test efficiency (at a small drop in accuracy), and it can also be applied to much longer video clips (over one minute long). Code and models are available at: https://github.com/facebookresearch/TimeSformer.

Video Transformers have become the prevalent solution for various video downstream tasks with superior expressive power and flexibility. However, these video transformers suffer from heavy computational costs induced by the massive number of tokens across the entire video frames, which has been the major barrier to training the model. Further, the patches irrelevant to the main contents, e.g., backgrounds, degrade the generalization performance of models. To tackle these issues, we propose training free token merging for lightweight video Transformer (vid-TLDR) that aims to enhance the efficiency of video Transformers by merging the background tokens without additional training. For vid-TLDR, we introduce a novel approach to capture the salient regions in videos only with the attention map. Further, we introduce the saliency-aware token merging strategy by dropping the background tokens and sharpening the object scores. Our experiments show that vid-TLDR significantly mitigates the computational complexity of video Transformers while achieving competitive performance compared to the base model without vid-TLDR. Code is available at https://github.com/mlvlab/vid-TLDR.

Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they exhibit limitations in tackling local video redundancy, due to the blind global comparison among tokens. UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format. However, this model has to require a tiresome and complicated image-pretraining phrase, before being finetuned on videos. This blocks its wide usage in practice. On the contrary, open-sourced ViTs are readily available and well-pretrained with rich image supervision. Based on these observations, we propose a generic paradigm to build a powerful family of video networks, by arming the pretrained ViTs with efficient UniFormer designs. We call this family UniFormerV2, since it inherits the concise style of the UniFormer block. But it contains brand-new local and global relation aggregators, which allow for preferable accuracy-computation balance by seamlessly integrating advantages from both ViTs and UniFormer. Without any bells and whistles, our UniFormerV2 gets the state-of-the-art recognition performance on 8 popular video benchmarks, including scene-related Kinetics-400/600/700 and Moments in Time, temporal-related Something-Something V1/V2, untrimmed ActivityNet and HACS. In particular, it is the first model to achieve 90% top-1 accuracy on Kinetics-400, to our best knowledge. Code will be available at https://github.com/OpenGVLab/UniFormerV2.

Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art, they have not explicitly modelled different spatiotemporal resolutions. To this end, we present Multiview Transformers for Video Recognition (MTV). Our model consists of separate encoders to represent different views of the input video with lateral connections to fuse information across views. We present thorough ablation studies of our model and show that MTV consistently performs better than single-view counterparts in terms of accuracy and computational cost across a range of model sizes. Furthermore, we achieve state-of-the-art results on six standard datasets, and improve even further with large-scale pretraining. Code and checkpoints are available at: https://github.com/google-research/scenic/tree/main/scenic/projects/mtv.

Law enforcement and city safety are significantly impacted by detecting violent incidents in surveillance systems. Although modern (smart) cameras are widely available and affordable, such technological solutions are impotent in most instances. Furthermore, personnel monitoring CCTV recordings frequently show a belated reaction, resulting in the potential cause of catastrophe to people and property. Thus automated detection of violence for swift actions is very crucial. The proposed solution uses a novel end-to-end deep learning-based video vision transformer (ViViT) that can proficiently discern fights, hostile movements, and violent events in video sequences. The study presents utilizing a data augmentation strategy to overcome the downside of weaker inductive biasness while training vision transformers on a smaller training datasets. The evaluated results can be subsequently sent to local concerned authority, and the captured video can be analyzed. In comparison to state-of-theart (SOTA) approaches the proposed method achieved auspicious performance on some of the challenging benchmark datasets.

Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, otherwise unnatural synchronization artifacts arise. Recent works have explored the progression of conditioning sound generators on still images and then video features, focusing on quality and semantic matching while ignoring synchronization, or by sacrificing some amount of quality to focus on improving synchronization only. In this work, we propose a V2A generative model, named MaskVAT, that interconnects a full-band high-quality general audio codec with a sequence-to-sequence masked generative model. This combination allows modeling both high audio quality, semantic matching, and temporal synchronicity at the same time. Our results show that, by combining a high-quality codec with the proper pre-trained audio-visual features and a sequence-to-sequence parallel structure, we are able to yield highly synchronized results on one hand, whilst being competitive with the state of the art of non-codec generative audio models. Sample videos and generated audios are available at https://maskvat.github.io .

We present a model for temporally precise action spotting in videos, which uses a dense set of detection anchors, predicting a detection confidence and corresponding fine-grained temporal displacement for each anchor. We experiment with two trunk architectures, both of which are able to incorporate large temporal contexts while preserving the smaller-scale features required for precise localization: a one-dimensional version of a u-net, and a Transformer encoder (TE). We also suggest best practices for training models of this kind, by applying Sharpness-Aware Minimization (SAM) and mixup data augmentation. We achieve a new state-of-the-art on SoccerNet-v2, the largest soccer video dataset of its kind, with marked improvements in temporal localization. Additionally, our ablations show: the importance of predicting the temporal displacements; the trade-offs between the u-net and TE trunks; and the benefits of training with SAM and mixup.

Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding. However, existing integration strategies suffer from several limitations: they either struggle to resolve distribution misalignment between reasoning and action spaces, underexploit the general reasoning capabilities of pretrained VLMs, or incur substantial inference latency during action policy generation, which degrades driving performance. To address these challenges, we propose \OURS in this work, an end-to-end AD framework that unifies reasoning and action generation within a single vision-language-action (VLA) model. Our approach leverages a mixture-of-transformer (MoT) architecture with joint attention sharing, which preserves the general reasoning capabilities of pre-trained VLMs while enabling efficient fast-slow inference through asynchronous execution at different task frequencies. Extensive experiments on multiple benchmarks, under both open- and closed-loop settings, demonstrate that \OURS achieves competitive performance compared to state-of-the-art methods. We further investigate the functional boundary of pre-trained VLMs in AD, examining when AD-tailored fine-tuning is necessary. Our results show that pre-trained VLMs can achieve competitive multi-task scene understanding performance through semantic prompting alone, while fine-tuning remains essential for action-level tasks such as decision-making and trajectory planning. We refer to https://automot-website.github.io/{Project Page} for the demonstration videos and qualitative results.

The increasing variety and quantity of tagged multimedia content on a variety of online platforms offer a unique opportunity to advance the field of human action recognition. In this study, we utilize 283,582 unique, unlabeled TikTok video clips, categorized into 386 hashtags, to train a domain-specific foundation model for action recognition. We employ VideoMAE V2, an advanced model integrating Masked Autoencoders (MAE) with Vision Transformers (ViT), pre-trained on this diverse collection of unstructured videos. Our model, fine-tuned on established action recognition benchmarks such as UCF101 and HMDB51, achieves state-of-the-art results: 99.05% on UCF101, 86.08% on HMDB51, 85.51% on Kinetics-400, and 74.27% on Something-Something V2 using the ViT-giant backbone. These results highlight the potential of using unstructured and unlabeled videos as a valuable source of diverse and dynamic content for training foundation models. Our investigation confirms that while initial increases in pre-training data volume significantly enhance model performance, the gains diminish as the dataset size continues to expand. Our findings emphasize two critical axioms in self-supervised learning for computer vision: (1) additional pre-training data can yield diminishing benefits for some datasets and (2) quality is more important than quantity in self-supervised learning, especially when building foundation models.

While large-scale robotic systems typically rely on textual instructions for tasks, this work explores a different approach: can robots infer the task directly from observing humans? This shift necessitates the robot's ability to decode human intent and translate it into executable actions within its physical constraints and environment. We introduce Vid2Robot, a novel end-to-end video-based learning framework for robots. Given a video demonstration of a manipulation task and current visual observations, Vid2Robot directly produces robot actions. This is achieved through a unified representation model trained on a large dataset of human video and robot trajectory. The model leverages cross-attention mechanisms to fuse prompt video features to the robot's current state and generate appropriate actions that mimic the observed task. To further improve policy performance, we propose auxiliary contrastive losses that enhance the alignment between human and robot video representations. We evaluate Vid2Robot on real-world robots, demonstrating a 20% improvement in performance compared to other video-conditioned policies when using human demonstration videos. Additionally, our model exhibits emergent capabilities, such as successfully transferring observed motions from one object to another, and long-horizon composition, thus showcasing its potential for real-world applications. Project website: vid2robot.github.io

Video action segmentation have been widely applied in many fields. Most previous studies employed video-based vision models for this purpose. However, they often rely on a large receptive field, LSTM or Transformer methods to capture long-term dependencies within videos, leading to significant computational resource requirements. To address this challenge, graph-based model was proposed. However, previous graph-based models are less accurate. Hence, this study introduces a graph-structured approach named Semantic2Graph, to model long-term dependencies in videos, thereby reducing computational costs and raise the accuracy. We construct a graph structure of video at the frame-level. Temporal edges are utilized to model the temporal relations and action order within videos. Additionally, we have designed positive and negative semantic edges, accompanied by corresponding edge weights, to capture both long-term and short-term semantic relationships in video actions. Node attributes encompass a rich set of multi-modal features extracted from video content, graph structures, and label text, encompassing visual, structural, and semantic cues. To synthesize this multi-modal information effectively, we employ a graph neural network (GNN) model to fuse multi-modal features for node action label classification. Experimental results demonstrate that Semantic2Graph outperforms state-of-the-art methods in terms of performance, particularly on benchmark datasets such as GTEA and 50Salads. Multiple ablation experiments further validate the effectiveness of semantic features in enhancing model performance. Notably, the inclusion of semantic edges in Semantic2Graph allows for the cost-effective capture of long-term dependencies, affirming its utility in addressing the challenges posed by computational resource constraints in video-based vision models.

Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and actions remain underexplored, especially for general-purpose scenarios and various forms of actions. To bridge this gap, we introduce Astra, an interactive general world model that generates real-world futures for diverse scenarios (e.g., autonomous driving, robot grasping) with precise action interactions (e.g., camera motion, robot action). We propose an autoregressive denoising architecture and use temporal causal attention to aggregate past observations and support streaming outputs. We use a noise-augmented history memory to avoid over-reliance on past frames to balance responsiveness with temporal coherence. For precise action control, we introduce an action-aware adapter that directly injects action signals into the denoising process. We further develop a mixture of action experts that dynamically route heterogeneous action modalities, enhancing versatility across diverse real-world tasks such as exploration, manipulation, and camera control. Astra achieves interactive, consistent, and general long-term video prediction and supports various forms of interactions. Experiments across multiple datasets demonstrate the improvements of Astra in fidelity, long-range prediction, and action alignment over existing state-of-the-art world models.

The canonical approach to video captioning dictates a caption generation model to learn from offline-extracted dense video features. These feature extractors usually operate on video frames sampled at a fixed frame rate and are often trained on image/video understanding tasks, without adaption to video captioning data. In this work, we present SwinBERT, an end-to-end transformer-based model for video captioning, which takes video frame patches directly as inputs, and outputs a natural language description. Instead of leveraging multiple 2D/3D feature extractors, our method adopts a video transformer to encode spatial-temporal representations that can adapt to variable lengths of video input without dedicated design for different frame rates. Based on this model architecture, we show that video captioning can benefit significantly from more densely sampled video frames as opposed to previous successes with sparsely sampled video frames for video-and-language understanding tasks (e.g., video question answering). Moreover, to avoid the inherent redundancy in consecutive video frames, we propose adaptively learning a sparse attention mask and optimizing it for task-specific performance improvement through better long-range video sequence modeling. Through extensive experiments on 5 video captioning datasets, we show that SwinBERT achieves across-the-board performance improvements over previous methods, often by a large margin. The learned sparse attention masks in addition push the limit to new state of the arts, and can be transferred between different video lengths and between different datasets. Code is available at https://github.com/microsoft/SwinBERT

Contemporary models for generating images show remarkable quality and versatility. Swayed by these advantages, the research community repurposes them to generate videos. Since video content is highly redundant, we argue that naively bringing advances of image models to the video generation domain reduces motion fidelity, visual quality and impairs scalability. In this work, we build Snap Video, a video-first model that systematically addresses these challenges. To do that, we first extend the EDM framework to take into account spatially and temporally redundant pixels and naturally support video generation. Second, we show that a U-Net - a workhorse behind image generation - scales poorly when generating videos, requiring significant computational overhead. Hence, we propose a new transformer-based architecture that trains 3.31 times faster than U-Nets (and is ~4.5 faster at inference). This allows us to efficiently train a text-to-video model with billions of parameters for the first time, reach state-of-the-art results on a number of benchmarks, and generate videos with substantially higher quality, temporal consistency, and motion complexity. The user studies showed that our model was favored by a large margin over the most recent methods. See our website at https://snap-research.github.io/snapvideo/.

Short-term action anticipation (STA) in first-person videos is a challenging task that involves understanding the next active object interactions and predicting future actions. Existing action anticipation methods have primarily focused on utilizing features extracted from video clips, but often overlooked the importance of objects and their interactions. To this end, we propose a novel approach that applies a guided attention mechanism between the objects, and the spatiotemporal features extracted from video clips, enhancing the motion and contextual information, and further decoding the object-centric and motion-centric information to address the problem of STA in egocentric videos. Our method, GANO (Guided Attention for Next active Objects) is a multi-modal, end-to-end, single transformer-based network. The experimental results performed on the largest egocentric dataset demonstrate that GANO outperforms the existing state-of-the-art methods for the prediction of the next active object label, its bounding box location, the corresponding future action, and the time to contact the object. The ablation study shows the positive contribution of the guided attention mechanism compared to other fusion methods. Moreover, it is possible to improve the next active object location and class label prediction results of GANO by just appending the learnable object tokens with the region of interest embeddings.

Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require additional task-specific information like goal states, making them not suited for open-ended tasks. To address these issues, we propose a two-stage framework for learning from visual observation. In the first stage, we introduce and pretrain State-to-Go (STG) Transformer offline to predict and differentiate latent transitions of demonstrations. Subsequently, in the second stage, the STG Transformer provides intrinsic rewards for downstream reinforcement learning tasks where an agent learns merely from intrinsic rewards. Empirical results on Atari and Minecraft show that our proposed method outperforms baselines and in some tasks even achieves performance comparable to the policy learned from environmental rewards. These results shed light on the potential of utilizing video-only data to solve difficult visual reinforcement learning tasks rather than relying on complete offline datasets containing states, actions, and rewards. The project's website and code can be found at https://sites.google.com/view/stgtransformer.

Procedural video representation learning is an active research area where the objective is to learn an agent which can anticipate and forecast the future given the present video input, typically in conjunction with textual annotations. Prior works often rely on large-scale pretraining of visual encoders and prediction models with language supervision. However, the necessity and effectiveness of extending compute intensive pretraining to learn video clip sequences with noisy text supervision have not yet been fully validated by previous works. In this work, we show that a strong off-the-shelf frozen pretrained visual encoder, along with a well designed prediction model, can achieve state-of-the-art (SoTA) performance in forecasting and procedural planning without the need for pretraining the prediction model, nor requiring additional supervision from language or ASR. Instead of learning representations from pixel space, our method utilizes the latent embedding space of publicly available vision encoders. By conditioning on frozen clip-level embeddings from observed steps to predict the actions of unseen steps, our prediction model is able to learn robust representations for forecasting through iterative denoising - leveraging the recent advances in diffusion transformers (Peebles & Xie, 2023). Empirical studies over a total of five procedural learning tasks across four datasets (NIV, CrossTask, COIN and Ego4D-v2) show that our model advances the strong baselines in long-horizon action anticipation (+2.6% in Verb ED@20, +3.1% in Noun ED@20), and significantly improves the SoTA in step forecasting (+5.0%), task classification (+3.8%), and procedure planning tasks (up to +2.28% in success rate, +3.39% in mAcc, and +0.90% in mIoU).

We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p, minute-scale videos with precise camera control. SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay, while significantly improving efficiency. Four core designs drive our architecture: (1) Hybrid Linear Attention combines frame-wise Gated DeltaNet (GDN) with softmax attention for memory-efficient long-context modeling. (2) Dual-Branch Camera Control ensures precise 6-DoF trajectory adherence. (3) Two-Stage Generation Pipeline applies a long-video refiner to stage-1 outputs, improving quality and consistency across sequences. (4) Robust Annotation Pipeline extracts accurate metric-scale 6-DoF camera poses from public videos to yield high-quality, spatiotemporally consistent action labels. Driven by these designs, SANA-WMdemonstrates remarkable efficiency across data, training compute, and inference hardware: it uses only sim213K public video clips with metric-scale pose supervision, completes training in 15 days on 64 H100s, and generates each 60s clip on a single GPU; its distilled variant can be deployed on a single RTX 5090 with NVFP4 quantization to denoise a 60s 720p clip in 34s. On our one-minute world-model benchmark, SANA-WM demonstrates stronger action-following accuracy than prior open-source baselines and achieves comparable visual quality at 36times higher throughput for scalable world modeling.

We explore a new task for audio-visual-language modeling called fine-grained audible video description (FAVD). It aims to provide detailed textual descriptions for the given audible videos, including the appearance and spatial locations of each object, the actions of moving objects, and the sounds in videos. Existing visual-language modeling tasks often concentrate on visual cues in videos while undervaluing the language and audio modalities. On the other hand, FAVD requires not only audio-visual-language modeling skills but also paragraph-level language generation abilities. We construct the first fine-grained audible video description benchmark (FAVDBench) to facilitate this research. For each video clip, we first provide a one-sentence summary of the video, ie, the caption, followed by 4-6 sentences describing the visual details and 1-2 audio-related descriptions at the end. The descriptions are provided in both English and Chinese. We create two new metrics for this task: an EntityScore to gauge the completeness of entities in the visual descriptions, and an AudioScore to assess the audio descriptions. As a preliminary approach to this task, we propose an audio-visual-language transformer that extends existing video captioning model with an additional audio branch. We combine the masked language modeling and auto-regressive language modeling losses to optimize our model so that it can produce paragraph-level descriptions. We illustrate the efficiency of our model in audio-visual-language modeling by evaluating it against the proposed benchmark using both conventional captioning metrics and our proposed metrics. We further put our benchmark to the test in video generation models, demonstrating that employing fine-grained video descriptions can create more intricate videos than using captions.

Action detection in real-world scenarios is particularly challenging due to densely distributed actions in hour-long untrimmed videos. It requires modeling both short- and long-term temporal relationships while handling significant intra-class temporal variations. Previous state-of-the-art (SOTA) Transformer-based architectures, though effective, are impractical for real-world deployment due to their high parameter count, GPU memory usage, and limited throughput, making them unsuitable for very long videos. In this work, we innovatively adapt the Mamba architecture for action detection and propose Multi-scale Temporal Mamba (MS-Temba), comprising two key components: Temporal Mamba (Temba) Blocks and the Temporal Mamba Fuser. Temba Blocks include the Temporal Local Module (TLM) for short-range temporal modeling and the Dilated Temporal SSM (DTS) for long-range dependencies. By introducing dilations, a novel concept for Mamba, TLM and DTS capture local and global features at multiple scales. The Temba Fuser aggregates these scale-specific features using Mamba to learn comprehensive multi-scale representations of untrimmed videos. MS-Temba is validated on three public datasets, outperforming SOTA methods on long videos and matching prior methods on short videos while using only one-eighth of the parameters.

We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions. Our approach consists of a powerful Action-conditioned motion TransFormer (ActFormer) under a GAN training scheme, equipped with a Gaussian Process latent prior. Such a design combines the strong spatio-temporal representation capacity of Transformer, superiority in generative modeling of GAN, and inherent temporal correlations from the latent prior. Furthermore, ActFormer can be naturally extended to multi-person motions by alternately modeling temporal correlations and human interactions with Transformer encoders. To further facilitate research on multi-person motion generation, we introduce a new synthetic dataset of complex multi-person combat behaviors. Extensive experiments on NTU-13, NTU RGB+D 120, BABEL and the proposed combat dataset show that our method can adapt to various human motion representations and achieve superior performance over the state-of-the-art methods on both single-person and multi-person motion generation tasks, demonstrating a promising step towards a general human motion generator.

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we introduce VideoMAP, a Hybrid Mamba-Transformer framework featuring a novel pre-training approach. VideoMAP uses a 4:1 Mamba-to-Transformer ratio, effectively balancing computational cost and model capacity. This architecture, combined with our proposed frame-wise masked autoregressive pre-training strategy, delivers significant performance gains when scaling to larger models. Additionally, VideoMAP exhibits impressive sample efficiency, significantly outperforming existing methods with less training data. Experiments show that VideoMAP outperforms existing models across various datasets, including Kinetics-400, Something-Something V2, Breakfast, and COIN. Furthermore, we demonstrate the potential of VideoMAP as a visual encoder for multimodal large language models, highlighting its ability to reduce memory usage and enable the processing of longer video sequences. The code is open-source at https://github.com/yunzeliu/MAP

Mainstream Video-Language Pre-training models actbert,clipbert,violet consist of three parts, a video encoder, a text encoder, and a video-text fusion Transformer. They pursue better performance via utilizing heavier unimodal encoders or multimodal fusion Transformers, resulting in increased parameters with lower efficiency in downstream tasks. In this work, we for the first time introduce an end-to-end video-language model, namely all-in-one Transformer, that embeds raw video and textual signals into joint representations using a unified backbone architecture. We argue that the unique temporal information of video data turns out to be a key barrier hindering the design of a modality-agnostic Transformer. To overcome the challenge, we introduce a novel and effective token rolling operation to encode temporal representations from video clips in a non-parametric manner. The careful design enables the representation learning of both video-text multimodal inputs and unimodal inputs using a unified backbone model. Our pre-trained all-in-one Transformer is transferred to various downstream video-text tasks after fine-tuning, including text-video retrieval, video-question answering, multiple choice and visual commonsense reasoning. State-of-the-art performances with the minimal model FLOPs on nine datasets demonstrate the superiority of our method compared to the competitive counterparts. The code and pretrained model have been released in https://github.com/showlab/all-in-one.

We study object interaction anticipation in egocentric videos. This task requires an understanding of the spatio-temporal context formed by past actions on objects, coined action context. We propose TransFusion, a multimodal transformer-based architecture. It exploits the representational power of language by summarizing the action context. TransFusion leverages pre-trained image captioning and vision-language models to extract the action context from past video frames. This action context together with the next video frame is processed by the multimodal fusion module to forecast the next object interaction. Our model enables more efficient end-to-end learning. The large pre-trained language models add common sense and a generalisation capability. Experiments on Ego4D and EPIC-KITCHENS-100 show the effectiveness of our multimodal fusion model. They also highlight the benefits of using language-based context summaries in a task where vision seems to suffice. Our method outperforms state-of-the-art approaches by 40.4% in relative terms in overall mAP on the Ego4D test set. We validate the effectiveness of TransFusion via experiments on EPIC-KITCHENS-100. Video and code are available at https://eth-ait.github.io/transfusion-proj/.

What if a video generation model could not only imagine a plausible future, but the correct one, accurately reflecting how the world changes with each action? We address this question by presenting the Egocentric World Model (EgoWM), a simple, architecture-agnostic method that transforms any pretrained video diffusion model into an action-conditioned world model, enabling controllable future prediction. Rather than training from scratch, we repurpose the rich world priors of Internet-scale video models and inject motor commands through lightweight conditioning layers. This allows the model to follow actions faithfully while preserving realism and strong generalization. Our approach scales naturally across embodiments and action spaces, ranging from 3-DoF mobile robots to 25-DoF humanoids, where predicting egocentric joint-angle-driven dynamics is substantially more challenging. The model produces coherent rollouts for both navigation and manipulation tasks, requiring only modest fine-tuning. To evaluate physical correctness independently of visual appearance, we introduce the Structural Consistency Score (SCS), which measures whether stable scene elements evolve consistently with the provided actions. EgoWM improves SCS by up to 80 percent over prior state-of-the-art navigation world models, while achieving up to six times lower inference latency and robust generalization to unseen environments, including navigation inside paintings.

World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in video generative models for developing world models at scale. This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction. iVideoGPT features a novel compressive tokenization technique that efficiently discretizes high-dimensional visual observations. Leveraging its scalable architecture, we are able to pre-train iVideoGPT on millions of human and robotic manipulation trajectories, establishing a versatile foundation that is adaptable to serve as interactive world models for a wide range of downstream tasks. These include action-conditioned video prediction, visual planning, and model-based reinforcement learning, where iVideoGPT achieves competitive performance compared with state-of-the-art methods. Our work advances the development of interactive general world models, bridging the gap between generative video models and practical model-based reinforcement learning applications.

We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the seminal Neural Turing Machine, and has an external memory consisting of a set of tokens which summarise the previous history (i.e., frames). This memory is efficiently addressed, read and written using a Transformer as the processing unit/controller at each step. The model's memory module ensures that a new observation will only be processed with the contents of the memory (and not the entire history), meaning that it can efficiently process long sequences with a bounded computational cost at each step. We show that TTM outperforms other alternatives, such as other Transformer models designed for long sequences and recurrent neural networks, on two real-world sequential visual understanding tasks: online temporal activity detection from videos and vision-based robot action policy learning. Code is publicly available at: https://github.com/google-research/scenic/tree/main/scenic/projects/token_turing

Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control. Existing methods either directly use parametric representations that fail to handle multi-shot generation or synthesize cross-paired data, which suffer from data scarcity, resulting in poor performance in complicated camera motion cloning. To address these issues, we introduce a general camera motion representation that encodes cameras as grid motion videos. This camera grid represents the camera parameters visually and supports the integration of diverse trajectories for multi-shot video generation. Building upon this, we propose OmniDirector, a unified framework trained on a million-scale camera grid-video pairs that coordinates characters, actions, and cameras to provide director-level control for multimodal diffusion transformers. Furthermore, we design a novel hierarchical prompt expansion agent that harmoniously integrates different control signals by systematically describing camera motion and visual content through understanding signal relationships. Extensive experiments demonstrate the superior performance and outstanding controllability of our framework. Project page: https://ymlinfeng.github.io/OmniDirector.github.io/

In this paper, we show that useful video representations can be learned from synthetic videos and natural images, without incorporating natural videos in the training. We propose a progression of video datasets synthesized by simple generative processes, that model a growing set of natural video properties (e.g. motion, acceleration, and shape transformations). The downstream performance of video models pre-trained on these generated datasets gradually increases with the dataset progression. A VideoMAE model pre-trained on our synthetic videos closes 97.2% of the performance gap on UCF101 action classification between training from scratch and self-supervised pre-training from natural videos, and outperforms the pre-trained model on HMDB51. Introducing crops of static images to the pre-training stage results in similar performance to UCF101 pre-training and outperforms the UCF101 pre-trained model on 11 out of 14 out-of-distribution datasets of UCF101-P. Analyzing the low-level properties of the datasets, we identify correlations between frame diversity, frame similarity to natural data, and downstream performance. Our approach provides a more controllable and transparent alternative to video data curation processes for pre-training.

We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of 512 times 896 resolution at 8 frames per second.

A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection via end-to-end training. To make it computationally feasible, prior works tend to "imagify" video inputs, i.e., a handful of sparsely sampled frames are fed into a 2D CNN, followed by a simple mean-pooling or concatenation to obtain the overall video representations. Although achieving promising results, such simple approaches may lose temporal information that is essential for performing downstream VidL tasks. In this work, we present VIOLET, a fully end-to-end VIdeO-LanguagE Transformer, which adopts a video transformer to explicitly model the temporal dynamics of video inputs. Further, unlike previous studies that found pre-training tasks on video inputs (e.g., masked frame modeling) not very effective, we design a new pre-training task, Masked Visual-token Modeling (MVM), for better video modeling. Specifically, the original video frame patches are "tokenized" into discrete visual tokens, and the goal is to recover the original visual tokens based on the masked patches. Comprehensive analysis demonstrates the effectiveness of both explicit temporal modeling via video transformer and MVM. As a result, VIOLET achieves new state-of-the-art performance on 5 video question answering tasks and 4 text-to-video retrieval tasks.

Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and memory storage. Each model needs an independent and complete finetuning process to adapt to different tasks, which limits its transferability to different visual domains. To address this challenge, we propose an effective adaptation approach for Transformer, namely AdaptFormer, which can adapt the pre-trained ViTs into many different image and video tasks efficiently. It possesses several benefits more appealing than prior arts. Firstly, AdaptFormer introduces lightweight modules that only add less than 2% extra parameters to a ViT, while it is able to increase the ViT's transferability without updating its original pre-trained parameters, significantly outperforming the existing 100\% fully fine-tuned models on action recognition benchmarks. Secondly, it can be plug-and-play in different Transformers and scalable to many visual tasks. Thirdly, extensive experiments on five image and video datasets show that AdaptFormer largely improves ViTs in the target domains. For example, when updating just 1.5% extra parameters, it achieves about 10% and 19% relative improvement compared to the fully fine-tuned models on Something-Something~v2 and HMDB51, respectively. Code is available at https://github.com/ShoufaChen/AdaptFormer.

We present VideoGPT: a conceptually simple architecture for scaling likelihood based generative modeling to natural videos. VideoGPT uses VQ-VAE that learns downsampled discrete latent representations of a raw video by employing 3D convolutions and axial self-attention. A simple GPT-like architecture is then used to autoregressively model the discrete latents using spatio-temporal position encodings. Despite the simplicity in formulation and ease of training, our architecture is able to generate samples competitive with state-of-the-art GAN models for video generation on the BAIR Robot dataset, and generate high fidelity natural videos from UCF-101 and Tumbler GIF Dataset (TGIF). We hope our proposed architecture serves as a reproducible reference for a minimalistic implementation of transformer based video generation models. Samples and code are available at https://wilson1yan.github.io/videogpt/index.html

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10x more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https://github.com/facebookresearch/SlowFast

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This thesis chronicles our endeavor to build multi-task models for generating videos and other modalities under diverse conditions, as well as for understanding and compression applications. Given the high dimensionality of visual data, we pursue concise and accurate latent representations. Our video-native spatial-temporal tokenizers preserve high fidelity. We unveil a novel approach to mapping bidirectionally between visual observation and interpretable lexical terms. Furthermore, our scalable visual token representation proves beneficial across generation, compression, and understanding tasks. This achievement marks the first instances of language models surpassing diffusion models in visual synthesis and a video tokenizer outperforming industry-standard codecs. Within these multi-modal latent spaces, we study the design of multi-task generative models. Our masked multi-task transformer excels at the quality, efficiency, and flexibility of video generation. We enable a frozen language model, trained solely on text, to generate visual content. Finally, we build a scalable generative multi-modal transformer trained from scratch, enabling the generation of videos containing high-fidelity motion with the corresponding audio given diverse conditions. Throughout the course, we have shown the effectiveness of integrating multiple tasks, crafting high-fidelity latent representation, and generating multiple modalities. This work suggests intriguing potential for future exploration in generating non-textual data and enabling real-time, interactive experiences across various media forms.

Adapting image models to the video domain has emerged as an efficient paradigm for solving video recognition tasks. Due to the huge number of parameters and effective transferability of image models, performing full fine-tuning is less efficient and even unnecessary. Thus, recent research is shifting its focus toward parameter-efficient image-to-video adaptation. However, these adaptation strategies inevitably introduce extra computational costs to deal with the domain gap and temporal modeling in videos. In this paper, we present a new adaptation paradigm (ZeroI2V) to transfer the image transformers to video recognition tasks (i.e., introduce zero extra cost to the original models during inference). To achieve this goal, we present two core designs. First, to capture the dynamics in videos and reduce the difficulty of image-to-video adaptation, we exploit the flexibility of self-attention and introduce spatial-temporal dual-headed attention (STDHA). This approach efficiently endows the image transformers with temporal modeling capability at zero extra parameters and computation. Second, to handle the domain gap between images and videos, we propose a linear adaption strategy that utilizes lightweight densely placed linear adapters to fully transfer the frozen image models to video recognition. Thanks to the customized linear design, all newly added adapters could be easily merged with the original modules through structural reparameterization after training, enabling zero extra cost during inference. Extensive experiments on representative fully-supervised and few-shot video recognition benchmarks showcase that ZeroI2V can match or even outperform previous state-of-the-art methods while enjoying superior parameter and inference efficiency.

We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.

An important challenge in vision-based action recognition is the embedding of spatiotemporal features with two or more heterogeneous modalities into a single feature. In this study, we propose a new 3D deformable transformer for action recognition with adaptive spatiotemporal receptive fields and a cross-modal learning scheme. The 3D deformable transformer consists of three attention modules: 3D deformability, local joint stride, and temporal stride attention. The two cross-modal tokens are input into the 3D deformable attention module to create a cross-attention token with a reflected spatiotemporal correlation. Local joint stride attention is applied to spatially combine attention and pose tokens. Temporal stride attention temporally reduces the number of input tokens in the attention module and supports temporal expression learning without the simultaneous use of all tokens. The deformable transformer iterates L-times and combines the last cross-modal token for classification. The proposed 3D deformable transformer was tested on the NTU60, NTU120, FineGYM, and PennAction datasets, and showed results better than or similar to pre-trained state-of-the-art methods even without a pre-training process. In addition, by visualizing important joints and correlations during action recognition through spatial joint and temporal stride attention, the possibility of achieving an explainable potential for action recognition is presented.

Video super-resolution (VSR) aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts. Although some progress has been made, there are grand challenges to effectively utilize temporal dependency in entire video sequences. Existing approaches usually align and aggregate video frames from limited adjacent frames (e.g., 5 or 7 frames), which prevents these approaches from satisfactory results. In this paper, we take one step further to enable effective spatio-temporal learning in videos. We propose a novel Trajectory-aware Transformer for Video Super-Resolution (TTVSR). In particular, we formulate video frames into several pre-aligned trajectories which consist of continuous visual tokens. For a query token, self-attention is only learned on relevant visual tokens along spatio-temporal trajectories. Compared with vanilla vision Transformers, such a design significantly reduces the computational cost and enables Transformers to model long-range features. We further propose a cross-scale feature tokenization module to overcome scale-changing problems that often occur in long-range videos. Experimental results demonstrate the superiority of the proposed TTVSR over state-of-the-art models, by extensive quantitative and qualitative evaluations in four widely-used video super-resolution benchmarks. Both code and pre-trained models can be downloaded at https://github.com/researchmm/TTVSR.

This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely, we seek to explain the decision-making process of video transformers based on high-level, spatiotemporal concepts that are automatically discovered. Prior research on concept-based interpretability has concentrated solely on image-level tasks. Comparatively, video models deal with the added temporal dimension, increasing complexity and posing challenges in identifying dynamic concepts over time. In this work, we systematically address these challenges by introducing the first Video Transformer Concept Discovery (VTCD) algorithm. To this end, we propose an efficient approach for unsupervised identification of units of video transformer representations - concepts, and ranking their importance to the output of a model. The resulting concepts are highly interpretable, revealing spatio-temporal reasoning mechanisms and object-centric representations in unstructured video models. Performing this analysis jointly over a diverse set of supervised and self-supervised representations, we discover that some of these mechanism are universal in video transformers. Finally, we demonstrate that VTCDcan be used to improve model performance for fine-grained tasks.

Video Language Models (VideoLMs) empower AI systems to understand temporal dynamics in videos. To fit to the maximum context window constraint, current methods use keyframe sampling which can miss both macro-level events and micro-level details due to the sparse temporal coverage. Furthermore, processing full images and their tokens for each frame incurs substantial computational overhead. To address these limitations, we propose to leverage video codec primitives (specifically motion vectors and residuals) which natively encode video redundancy and sparsity without requiring expensive full-image encoding for most frames. To this end, we introduce lightweight transformer-based encoders that aggregate codec primitives and align their representations with image encoder embeddings through a pre-training strategy that accelerates convergence during end-to-end fine-tuning. Our approach reduces the time-to-first-token by up to 86% and token usage by up to 93% compared to standard VideoLMs. Moreover, by varying the keyframe and codec primitive densities we are able to maintain or exceed performance on 14 diverse video understanding benchmarks spanning general question answering, temporal reasoning, long-form understanding, and spatial scene understanding.

This study seeks to automate camera movement control for filming existing subjects into attractive videos, contrasting with the creation of non-existent content by directly generating the pixels. We select drone videos as our test case due to their rich and challenging motion patterns, distinctive viewing angles, and precise controls. Existing AI videography methods struggle with limited appearance diversity in simulation training, high costs of recording expert operations, and difficulties in designing heuristic-based goals to cover all scenarios. To avoid these issues, we propose a scalable method that involves collecting real-world training data to improve diversity, extracting camera trajectories automatically to minimize annotation costs, and training an effective architecture that does not rely on heuristics. Specifically, we collect 99k high-quality trajectories by running 3D reconstruction on online videos, connecting camera poses from consecutive frames to formulate 3D camera paths, and using Kalman filter to identify and remove low-quality data. Moreover, we introduce DVGFormer, an auto-regressive transformer that leverages the camera path and images from all past frames to predict camera movement in the next frame. We evaluate our system across 38 synthetic natural scenes and 7 real city 3D scans. We show that our system effectively learns to perform challenging camera movements such as navigating through obstacles, maintaining low altitude to increase perceived speed, and orbiting towers and buildings, which are very useful for recording high-quality videos. Data and code are available at dvgformer.github.io.

Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video streams frame by frame, preserve historical information, and make low-latency decisions. To address these challenges, our main contributions are three-fold. (i) We develop a novel streaming video backbone, termed as StreamFormer, by incorporating causal temporal attention into a pre-trained vision transformer. This enables efficient streaming video processing while maintaining image representation capability. (ii) To train StreamFormer, we propose to unify diverse spatial-temporal video understanding tasks within a multitask visual-language alignment framework. Hence, StreamFormer learns global semantics, temporal dynamics, and fine-grained spatial relationships simultaneously. (iii) We conduct extensive experiments on online action detection, online video instance segmentation, and video question answering. StreamFormer achieves competitive results while maintaining efficiency, demonstrating its potential for real-time applications.

We introduce LTX-Video, a transformer-based latent diffusion model that adopts a holistic approach to video generation by seamlessly integrating the responsibilities of the Video-VAE and the denoising transformer. Unlike existing methods, which treat these components as independent, LTX-Video aims to optimize their interaction for improved efficiency and quality. At its core is a carefully designed Video-VAE that achieves a high compression ratio of 1:192, with spatiotemporal downscaling of 32 x 32 x 8 pixels per token, enabled by relocating the patchifying operation from the transformer's input to the VAE's input. Operating in this highly compressed latent space enables the transformer to efficiently perform full spatiotemporal self-attention, which is essential for generating high-resolution videos with temporal consistency. However, the high compression inherently limits the representation of fine details. To address this, our VAE decoder is tasked with both latent-to-pixel conversion and the final denoising step, producing the clean result directly in pixel space. This approach preserves the ability to generate fine details without incurring the runtime cost of a separate upsampling module. Our model supports diverse use cases, including text-to-video and image-to-video generation, with both capabilities trained simultaneously. It achieves faster-than-real-time generation, producing 5 seconds of 24 fps video at 768x512 resolution in just 2 seconds on an Nvidia H100 GPU, outperforming all existing models of similar scale. The source code and pre-trained models are publicly available, setting a new benchmark for accessible and scalable video generation.

In this research, we present a novel approach to motion customization in video generation, addressing the widespread gap in the thorough exploration of motion representation within video generative models. Recognizing the unique challenges posed by video's spatiotemporal nature, our method introduces Motion Embeddings, a set of explicit, temporally coherent one-dimensional embeddings derived from a given video. These embeddings are designed to integrate seamlessly with the temporal transformer modules of video diffusion models, modulating self-attention computations across frames without compromising spatial integrity. Our approach offers a compact and efficient solution to motion representation and enables complex manipulations of motion characteristics through vector arithmetic in the embedding space. Furthermore, we identify the Temporal Discrepancy in video generative models, which refers to variations in how different motion modules process temporal relationships between frames. We leverage this understanding to optimize the integration of our motion embeddings. Our contributions include the introduction of a tailored motion embedding for customization tasks, insights into the temporal processing differences in video models, and a demonstration of the practical advantages and effectiveness of our method through extensive experiments.

Understanding videos is one of the fundamental directions in computer vision research, with extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and Transformers. The newly proposed architecture of state space model, e.g., Mamba, shows promising traits to extend its success in long sequence modeling to video modeling. To assess whether Mamba can be a viable alternative to Transformers in the video understanding domain, in this work, we conduct a comprehensive set of studies, probing different roles Mamba can play in modeling videos, while investigating diverse tasks where Mamba could exhibit superiority. We categorize Mamba into four roles for modeling videos, deriving a Video Mamba Suite composed of 14 models/modules, and evaluating them on 12 video understanding tasks. Our extensive experiments reveal the strong potential of Mamba on both video-only and video-language tasks while showing promising efficiency-performance trade-offs. We hope this work could provide valuable data points and insights for future research on video understanding. Code is public: https://github.com/OpenGVLab/video-mamba-suite.

Recently, action recognition has been dominated by transformer-based methods, thanks to their spatiotemporal contextual aggregation capacities. However, despite the significant progress achieved on scene-related datasets, they do not perform well on motion-sensitive datasets due to the lack of elaborate motion modeling designs. Meanwhile, we observe that the widely-used cost volume in traditional action recognition is highly similar to the affinity matrix defined in self-attention, but equipped with powerful motion modeling capacities. In light of this, we propose to integrate those effective motion modeling properties into the existing transformer in a unified and neat way, with the proposal of the Explicit Motion Information Mining module (EMIM). In EMIM, we propose to construct the desirable affinity matrix in a cost volume style, where the set of key candidate tokens is sampled from the query-based neighboring area in the next frame in a sliding-window manner. Then, the constructed affinity matrix is used to aggregate contextual information for appearance modeling and is converted into motion features for motion modeling as well. We validate the motion modeling capacities of our method on four widely-used datasets, and our method performs better than existing state-of-the-art approaches, especially on motion-sensitive datasets, i.e., Something-Something V1 & V2.

In-context learning for vision data has been underexplored compared with that in natural language. Previous works studied image in-context learning, urging models to generate a single image guided by demonstrations. In this paper, we propose and study video in-context learning, where the model starts from an existing video clip and generates diverse potential future sequences, each semantically guided by the prompted video demonstrations. To achieve this, we provide a clear definition of the task, and train an autoregressive Transformer on video datasets. We thoroughly analyze the effect of different datasets and represent frames as discrete tokens, and then model them by next token predictions. We design various evaluation metrics, including both objective and subjective measures, to demonstrate the visual quality and semantic accuracy of generation results. Our model follows the scaling law and generates high-quality video clips that accurately align with the semantic guidance provided by in-context examples.