Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models Paper • 2606.25041 • Published 18 days ago • 115
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation Paper • 2605.18739 • Published May 18 • 116
Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion Paper • 2604.24351 • Published Apr 27 • 11
Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion Paper • 2604.24351 • Published Apr 27 • 11
AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation Paper • 2603.28068 • Published Mar 31 • 13
DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning Paper • 2603.12257 • Published Mar 12 • 31
DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning Paper • 2603.12257 • Published Mar 12 • 31
The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training Paper • 2603.10444 • Published Mar 11 • 12
SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature Paper • 2601.10108 • Published Jan 15 • 7
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Paper • 2512.08765 • Published Dec 9, 2025 • 134