6 citations · 7 across the 6 of their papers we have counts for
4 papers · 1 filter
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
Xinmu Ge, Zizhuo Zhang, Yu Huang +9
On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning. Under the reverse KL objective, the idealized optimum of OPD aligns the…
Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
Yu Huang, Zihua Zhao, Zhaoxin Huan +9
The open-ended generation in LLMs usually requires multi-dimensional rubrics to adequately assess quality and guide the improvement of reinforcement learning. However, a critical d…
Bootstrapping your behavior: a new pretraining strategy for user behavior sequence data
Weichang Wu, Xiaolu Zhang, Jun Zhou +2
User Behavior Sequence (UBS) modeling is crucial in industrial applications. As data scale and task diversity grow, UBS pretraining methods have become increasingly pivotal. State-…
An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training
Youshao Xiao, Zhenglei Zhou, Fagui Mao +6
Recently, ChatGPT or InstructGPT like large language models (LLM) has made a significant impact in the AI world. Many works have attempted to reproduce the complex InstructGPT's tr…