10 papers
Decoupled Contrastive Decoding via Expert-Aligned Drafting
Zhixuan Liu, Zhichen Dong, Yuanfu Wang +1
Contrastive Decoding (CD) improves generation quality, but its amateur-model pass makes decoding expensive. Accelerating CD with speculative decoding raises a proposal-alignment qu…
Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
Xiaoying Zhang, Yipeng Zhang, Hao Sun +4
Recent advances in reinforcement learning (RL) using numerical rewards have significantly enhanced the complex reasoning capabilities of large language models (LLMs). However, we i…
Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
Yuanfu Wang, Zhixuan Liu, Xiangtian Li +2
The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally con…
Emergent Response Planning in LLMs
Zhichen Dong, Zhanhui Zhou, Zhixuan Liu +2
In this work, we argue that large language models (LLMs), though trained to predict only the next token, exhibit emergent planning behaviors: $\textbf{their hidden representations…
RePO: Replay-Enhanced Policy Optimization
Siheng Li, Zhanhui Zhou, Wai Lam +2
Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy out…
SafeCoT: Improving VLM Safety with Minimal Reasoning
Jiachen Ma, Zhanhui Zhou, Chao Yang +1
Ensuring safe and appropriate responses from vision-language models (VLMs) remains a critical challenge, particularly in high-risk or ambiguous scenarios. We introduce SafeCoT, a l…