Yingmin Qiu — accepted AI-conference papers

2026

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

Xinrong Chen, Xu Chu, Yingmin Qiu, Hengyuan Zhang, Jing Xiong, Shiyu Tang +5

CVPR 2026

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 often produce hallucinations. Hallucinations denote generated content that is grammatically and syntactically coherent,

Cited by 0 Source ↗Scholar ↗

2025

GuiLoMo: Allocating Experts and Ranks for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors

Xinrong Chen, Hengyuan Zhang, Yingmin Qiu, Xiao Liang, Ziyue Li, Guanyu Wang +4

EMNLP 2025

Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. However, their performance is limited by the small number of trainable parameters. Recent work combines LoRA with the Mixtu

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗