TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published 1 day ago • 60
DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning Paper • 2603.12257 • Published 26 days ago • 31
DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning Paper • 2603.12257 • Published 26 days ago • 31
DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning Paper • 2603.12257 • Published 26 days ago • 31
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning Paper • 2603.00889 • Published Mar 1 • 56
Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory Paper • 2602.02393 • Published Feb 2 • 18
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis Paper • 2602.03139 • Published Feb 3 • 45
SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature Paper • 2601.10108 • Published Jan 15 • 7
X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests Paper • 2601.06953 • Published Jan 11 • 46
Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding Paper • 2512.17532 • Published Dec 19, 2025 • 68
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Paper • 2512.08765 • Published Dec 9, 2025 • 134
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Paper • 2512.08765 • Published Dec 9, 2025 • 134
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Paper • 2512.08765 • Published Dec 9, 2025 • 134 • 5