Xiangyu Lu — accepted AI-conference papers

2026

Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning

(Andrew) Zhanke Zhou, Xiangyu Lu, Chentao Cao, Brando Miranda, Tongliang Liu, Bo Han +1

ICML 2026poster

RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often uses uniform sampling and near-uniform weighting, leading to inefficient computation allocation. We study GRPO by tracking token log-probabilities, group-normalized advantages, and induced toke…

Cited by 0 Source ↗Scholar ↗

2025

LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation

Hongyun Zhou, Xiangyu Lu, Wang Xu, Conghui Zhu, Tiejun Zhao, Muyun Yang

COLING 2025main

Low-Rank Adaptation (LoRA) is currently the most commonly used Parameter-efficient fine-tuning (PEFT) method. However, it still faces high computational and storage costs to models with billions of parameters. Most previous studies have tackled this issue by using pruning techniques. Nonetheless, th…

Cited by 20 Source ↗PDF ↗Scholar ↗