collaborators

10 papers

cs.CL2026

InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning

Junyou Su, He Zhu, Xiao Luo +6

Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing returns. Existing data se…

cs.CL2025

G2: Guided Generation for Enhanced Output Diversity in LLMs

Zhiwen Ruan, Yixia Li, Yefeng Liu +5

Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, these models exhibit a critical limitation in outp…

cs.CL2025

Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning

Zhiwen Ruan, Yixia Li, He Zhu +4

Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. How…

cs.CL2025

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks

Zhiwen Ruan, Yun Chen, Yutao Hou +3

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the le…

cs.CV2025

PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language Models

Wanru Zhuang, Wenbo Li, Zhibin Lan +3

Text Image Machine Translation (TIMT) aims to translate texts embedded within an image into another language. Current TIMT studies primarily focus on providing translations for all…

cs.AI2025

FormaRL: Enhancing Autoformalization with no Labeled Data

Yanxing Huang, Xinling Jin, Sijie Liang +2

Autoformalization is one of the central tasks in formal verification, while its advancement remains hindered due to the data scarcity and the absence efficient methods. In this wor…