5 papers
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang +4
Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely used critic-free RL methods rel…
Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning
Zicheng Xu, Ruixuan Zhang, Yu-Neng Chuang +7
Large Language Models (LLMs) achieve remarkable reasoning capabilities through reinforcement learning (RL) post-training. However, existing RL post-training commonly relies on unif…
DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
Zicheng Xu, Xiuyi Lou, Guanchu Wang +6
Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectori…
Why and How Auxiliary Tasks Improve JEPA Representations
Jiacan Yu, Siyi Chen, Mingrui Liu +5
Joint-Embedding Predictive Architecture (JEPA) is increasingly used for visual representation learning and as a component in model-based RL, but its behavior remains poorly underst…
Self-ensemble: Mitigating Confidence Mis-calibration for Large Language Models
Zicheng Xu, Guanchu Wang, Guangyao Zheng +4
Although Large Language Models (LLMs) perform well in general fields, they exhibit a confidence distortion problem on multi-choice question-answering (MCQA), particularly as the nu…