MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
Paper • 2511.18373 • Published • 7
My thing
-
-
Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO
Paper • 2511.13288 • Published • 19 -
Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
Paper • 2511.19418 • Published • 29 -
SAM 3: Segment Anything with Concepts
Paper • 2511.16719 • Published • 133 -
Temporal Prompting Matters: Rethinking Referring Video Object Segmentation
Paper • 2510.07319 • Published • 3 -
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 94 -
O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
Paper • 2511.13593 • Published • 28 -
RynnVLA-002: A Unified Vision-Language-Action and World Model
Paper • 2511.17502 • Published • 28 -
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Paper • 2511.11007 • Published • 15 -
Depth Anything 3: Recovering the Visual Space from Any Views
Paper • 2511.10647 • Published • 101 -
LightRAG: Simple and Fast Retrieval-Augmented Generation
Paper • 2410.05779 • Published • 31 -
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 121 -
TradingAgents: Multi-Agents LLM Financial Trading Framework
Paper • 2412.20138 • Published • 24 -
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation
Paper • 2410.17799 • Published • 12 -
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
Paper • 2511.13648 • Published • 53 -
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Paper • 2509.22186 • Published • 152 -
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Paper • 2510.15869 • Published • 50 -
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization
Paper • 2511.15705 • Published • 98 -
FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
Paper • 2510.22543 • Published • 14 -
Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning
Paper • 2511.19900 • Published • 49 -
From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models
Paper • 2512.10867 • Published • 16 -
Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
Paper • 2503.04721 • Published • 4 -
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper • 2603.17187 • Published • 90 -
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
Paper • 2603.17117 • Published • 69 -
Complementary Reinforcement Learning
Paper • 2603.17621 • Published • 28 -
AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
Paper • 2603.16496 • Published • 8 -
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
Paper • 2603.18004 • Published • 5 -
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
Paper • 2603.13398 • Published • 135 -
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
Paper • 2603.16669 • Published • 65 -
Efficient Reasoning on the Edge
Paper • 2603.16867 • Published • 15 -
SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
Paper • 2603.16864 • Published • 14 -
Omnilingual MT: Machine Translation for 1,600 Languages
Paper • 2603.16309 • Published • 12 -
ViT-AdaLA: Adapting Vision Transformers with Linear Attention
Paper • 2603.16063 • Published • 2 -
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
Paper • 2603.15594 • Published • 136 -
Mixture-of-Depths Attention
Paper • 2603.15619 • Published • 71 -
Can Vision-Language Models Solve the Shell Game?
Paper • 2603.08436 • Published • 37 -
Multimodal OCR: Parse Anything from Documents
Paper • 2603.13032 • Published • 29 -
NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval
Paper • 2603.12824 • Published • 5