TurnWise is proposed, a turn-level GRPO framework that aligns learning with individual streaming decisions and addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing redundancy in streaming video understanding.
Shuai Dong, Kang-Hui Tian, Ling-Han Chen et al.· 0 citations
This work introduces CUA-Master, a nested double-loop recursive improvement framework that substantially improves the quality and efficiency of data synthesis, and exhibits continuous gains across recursive iterations.
Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were achieved. Scaling either trajectory coverage or verification alone is insufficient as new environments introduce distinct states, rules, and dependencies that must also be re...
Xiao-Yang Yuan, Ji Zhao, Xing-Yu Hu et al.· 0 citations
The results support OPD as preparation for RL and favor forward KL when OPD is followed by RL in the authors' comparison, which highlights the importance of both objective choice and the states receiving supervision for subsequent RL.
This work proposes a streaming recognition and gated LoRA framework for intrinsic VLM safety, which is trained from unsafe prefixes, transition statements, and safe continuations, so that it learns to redirect unsafe generations back to safe responses after activation.
Cao-Yuan Ma, Tian Gu, Wen-Pu Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.