3 papers
cs.LG2026
Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control
Bolian Li, Yifan Wang, Yi Ding +3
Reinforcement learning (RL) has enabled complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performance saturation, preventing cont…
cs.CL2025
Unlocking Multimodal Mathematical Reasoning via Process Reward Model
Ruilin Luo, Zhuofan Zheng, Yifan Wang +9
Process Reward Models (PRMs) have shown promise in enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) through Test-Time Scaling (TTS). However, their…
cs.AI2025
Enhancing Large Language Model Performance with Gradient-Based Parameter Selection
Haoling Li, Xin Zhang, Xiao Liu +4
Large language models (LLMs) have revolutionized lots of fields of research. Although it is well-known that fine-tuning is essential for enhancing the capabilities of LLMs, existin…