collaborators

7 papers

cs.LG2026

From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment

Hao Chen, Qi Zhang, Liyao Li +7

Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selecti…

cs.CL2026

Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination

Lirong Gao, Zeqing Wang, Yuyan Cai +6

While Large Language Models (LLMs) have increasingly assisted in historical tasks such as text processing, their capacity for professional-level historical reasoning remains undere…

cs.AI2026

Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty

Zewei Yu, Lirong Gao, Yuke Zhu +4

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks by employing test-time scaling. However, they often generate over-long chains-of-t…

cs.CL2025

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models

Hao Chen, Haoze Li, Zhiqing Xiao +6

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance…

cs.LG2025

FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts

Xinyi Wang, Lirong Gao, Haobo Wang +2

Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a widely adopted strategy for adapting pre-trained Large Language Models (LLMs) to downstream tasks, significantly re…

cs.CL2025

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization

Qi Zhang, Shouqing Yang, Lirong Gao +8

Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses o…