AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation Paper • 2602.04672 • Published Feb 4 • 4
From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping Paper • 2610.26681 • Published 21 days ago • 19
CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding Paper • 2609.40048 • Published Sep 30 • 13
Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Paper • 2606.03577 • Published Jun 2 • 17
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration? Paper • 2606.01247 • Published May 31 • 29
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation Paper • 2604.24764 • Published Apr 27 • 120
Exploring Spatial Intelligence from a Generative Perspective Paper • 2604.20570 • Published Apr 22 • 23
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering Paper • 2604.08209 • Published Apr 9 • 25
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality Paper • 2512.07951 • Published Dec 8, 2025 • 51
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs Paper • 2510.13795 • Published Oct 15, 2025 • 61
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks Paper • 2502.17157 • Published Feb 24, 2025 • 52