Video diffusion and flow models require many sequential evaluations, making generation computationally expensive. Few-step distillation reduces this cost but poses a capacity allocation problem: a student must match the teacher's iterative generation with far less sequential computation. Existing trajectory methods ask...
Lang Feng, Péter Karkus, M. Igl et al.· 0 citations
Autonomous driving has made remarkable progress through imitation learning with massive human demonstration data. However, a trained planner often degrades severely when applied to a new environment zero-shot, because of domain shifts in traffic regulations, road layout and driving behaviors. Therefore, adapting a traj...
Weijiang Xiong, Lang Feng, Alexandre Alahi et al.· 0 citations
It is shown that under GRPO-style optimization, a global normalization baseline may deviate from diverse agents'reward distributions, which ultimately leads to gradient-norm instability, which theoretically pinpoints a key reason for training instability when extending group-based RL to multi-agent LLM systems.
Lang Feng, Long-Tao Zheng, Shuo He et al.· arXiv.org· 14 citations· ⚡1
SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and distills their behavioral effect back into the policy model, is proposed.
Jinyang Wu, Shuo Yang, Zhengxi Lu et al.· arXiv.org· 7 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
