HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
Paper • 2603.17024 • Published • 110
From Vision to Motion
-
-
WorldAgents: Can Foundation Image Models be Agents for 3D World Models?
Paper • 2603.19708 • Published • 13 -
MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
Paper • 2603.25319 • Published • 32 -
ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions
Paper • 2603.25791 • Published • 7 -
Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
Paper • 2604.03016 • Published • 37 -
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Paper • 2604.02029 • Published • 152 -
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 203 -
Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions
Paper • 2604.23774 • Published • 17 -
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
Paper • 2605.00503 • Published • 13 -
Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
Paper • 2605.04128 • Published • 17 -
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
Paper • 2605.10780 • Published • 33 -
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
Paper • 2605.25979 • Published • 27 -
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
Paper • 2605.28774 • Published • 93 -
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Paper • 2605.31604 • Published • 63 -
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data
Paper • 2507.07095 • Published • 56 -
VideoMDM: Towards 3D Human Motion Generation From 2D Supervision
Paper • 2606.13364 • Published • 20 -
Motion4Motion: Motion Transfer Across Subjects at Inference
Paper • 2607.11644 • Published • 9 -
Latent-Identity Tuning in Text-to-Image Personalization Models
Paper • 2607.11885 • Published • 10 -
4D Human-Scene Reconstruction from Low-Overlap Captures
Paper • 2607.09125 • Published • 49 -
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Paper • 2606.28128 • Published • 52 -
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
Paper • 2606.25041 • Published • 119 -
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Paper • 2607.14935 • Published • 116