10 papers
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…
Training Large Reasoning Models Efficiently via Progressive Thought Encoding
Zeliang Zhang, Xiaodong Liu, Hao Cheng +3
Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rew…
Improving Interactive In-Context Learning from Natural Language Feedback
Martin Klissarov, Jonathan Cook, Diego Antognini +5
Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large langua…
Why mask diffusion does not work
Haocheng Sun, Cynthia Xin Wen, Edward Hong Wang
The main advantages of diffusion language models over autoregressive (AR) models lie in their ability to support parallel generation and bidirectional attention, enabling a more co…
ViSS-R1: Self-Supervised Reinforcement Video Reasoning
Bo Fang, Yuxin Song, Qiangqiang Wu +3
Complex video reasoning remains a significant challenge for Multimodal Large Language Models (MLLMs), as current R1-based methodologies often prioritize text-centric reasoning deri…
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
Hao Sun, Mihaela van der Schaar
In the era of Large Language Models (LLMs), alignment has emerged as a fundamental yet challenging problem in the pursuit of more reliable, controllable, and capable machine intell…