5 papers
ACPO: Asymmetric Credit Policy Optimization via Mode-Local Entropy Surrogate
Zijun Xie, Yuyang You, Yongzhi Li +8
Outcome-supervised reinforcement learning scales to verifiable reasoning tasks, but trajectory-level rewards assign the same outcome signal to all sampled tokens, overlooking their…
MuSteerNet: Human Reaction Generation from Videos via Observation-Reaction Mutual Steering
Yuan Zhou, Yongzhi Li, Yanqi Dai +6
Video-driven human reaction generation aims to synthesize 3D human motions that directly react to observed video sequences, which is crucial for building human-like interactive AI…
AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation
Milton Zhou, Sizhong Qin, Yongzhi Li +2
Short-form videos have become a primary medium for digital advertising, requiring scalable and efficient content creation. However, current workflows and AI tools remain disjoint a…
Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
Yuyang You, Yongzhi Li, Jiahui Li +3
Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillat…
Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning
Zhengjian Yao, Yongzhi Li, Xinyuan Gao +3
We present "Narrative Weaver", a novel framework that addresses a fundamental challenge in generative AI: achieving multi-modal controllable, long-range, and consistent visual cont…