collaborators

8 papers

cs.LG2026

Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization

Xu Chu, Guanyu Wang, Zhijie Tan +4

Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness limits the model's applications…

cs.CV2026

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance

Xinrong Chen, Xu Chu, Yingmin Qiu +8

Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and…

cs.LG2026

Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity

Hengyuan Zhang, Xinrong Chen, Zunhai Su +10

Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing me…

cs.MM2026

MORE-R1: Guiding LVLM for Multimodal Object-Entity Relation Extraction via Stepwise Reasoning with Reinforcement Learning

Xiang Yuan, Xu Chu, Xinrong Chen +6

Multimodal Object-Entity Relation Extraction (MORE) is a challenging task in information extraction research. It aims to identify relations between visual objects and textual entit…

cs.MM2025

Stepwise Schema-Guided Prompting Framework with Parameter Efficient Instruction Tuning for Multimedia Event Extraction

Xiang Yuan, Xinrong Chen, Haochen Li +4

Multimedia Event Extraction (MEE) has become an important task in information extraction research as news today increasingly prefers to contain multimedia content. Current MEE work…

cs.CL2025

GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors

Hengyuan Zhang, Xinrong Chen, Yingmin Qiu +7

Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. How…