GenTron: Delving Deep into Diffusion Transformers for Image and Video Generation
Paper • 2312.04557 • Published • 13
daily papers
-
-
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models
Paper • 2312.04410 • Published • 15 -
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
Paper • 2312.04461 • Published • 62 -
Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
Paper • 2401.02955 • Published • 23 -
Denoising Vision Transformers
Paper • 2401.02957 • Published • 32 -
SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation
Paper • 2312.16272 • Published • 7 -
PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion
Paper • 2312.16486 • Published • 7 -
Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models
Paper • 2411.07126 • Published • 30 -
Motion Control for Enhanced Complex Action Video Generation
Paper • 2411.08328 • Published • 5 -
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
Paper • 2411.07975 • Published • 32 -
Pyramidal Flow Matching for Efficient Video Generative Modeling
Paper • 2410.05954 • Published • 41 -
Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
Paper • 2412.04432 • Published • 16 -
LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
Paper • 2412.04814 • Published • 46 -
Mind the Time: Temporally-Controlled Multi-Event Video Generation
Paper • 2412.05263 • Published • 10 -
OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
Paper • 2412.01169 • Published • 13 -
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
Paper • 2410.13861 • Published • 56 -
UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency
Paper • 2412.15216 • Published • 5 -
MotiF: Making Text Count in Image Animation with Motion Focal Loss
Paper • 2412.16153 • Published • 6 -
Large Motion Video Autoencoding with Cross-modal Video VAE
Paper • 2412.17805 • Published • 24 -
AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation
Paper • 2501.09503 • Published • 14 -
Do generative video models learn physical principles from watching videos?
Paper • 2501.09038 • Published • 33 -
Small Models Struggle to Learn from Strong Reasoners
Paper • 2502.12143 • Published • 40 -
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
Paper • 2503.21755 • Published • 33 -
Efficient Generative Model Training via Embedded Representation Warmup
Paper • 2504.10188 • Published • 12 -
Video-As-Prompt: Unified Semantic Control for Video Generation
Paper • 2510.20888 • Published • 50 -
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Paper • 2511.09611 • Published • 72 -
TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
Paper • 2511.13704 • Published • 44 -
Back to Basics: Let Denoising Generative Models Denoise
Paper • 2511.13720 • Published • 71 -
DiP: Taming Diffusion Models in Pixel Space
Paper • 2511.18822 • Published • 31 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 171 -
PixelDiT: Pixel Diffusion Transformers for Image Generation
Paper • 2511.20645 • Published • 39 -
OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Paper • 2603.24458 • Published • 10 -
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
Paper • 2603.23500 • Published • 37 -
Manifold-Aware Exploration for Reinforcement Learning in Video Generation
Paper • 2603.21872 • Published • 34 -
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss
Paper • 2608.11205 • Published • 27 -
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
Paper • 2608.17402 • Published • 14 -
V-RAE: Rethinking Video Latent Spaces for Generation
Paper • 2608.13556 • Published • 26 -
AVA-Encoder: Towards Agent-Native Video Representation Learning
Paper • 2608.12313 • Published • 40 -
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Paper • 2608.13558 • Published • 85 -
VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation
Paper • 2608.18607 • Published • 9 -
ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models
Paper • 2608.14022 • Published • 13