4 papers
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
Zikang Shan, Han Zhong, Liwei Wang +1
Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained advantage estimation based on a…
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Yuliang Liu, Junjie Lu, Zhaoling Chen +10
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefin…
DPO Meets PPO: Reinforced Token Optimization for RLHF
Han Zhong, Zikang Shan, Guhao Feng +6
In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards -- a chall…
Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
Wentao Zhang, Junliang Guo, Tianyu He +3
People interact with the real-world largely dependent on visual signal, which are ubiquitous and illustrate detailed demonstrations. In this paper, we explore utilizing visual sign…