GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published 5 days ago • 166
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times Paper • 2512.16093 • Published 27 days ago • 93
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published 27 days ago • 60
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows Paper • 2512.16969 • Published 26 days ago • 112
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Paper • 2512.08765 • Published Dec 9, 2025 • 128