collaborators

6 papers

cs.MM2026

Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination

Yangneng Chen, Junlin Li, Weijun Yao +4

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by hallucinations-generating text that…

cs.CL2026

Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework

Xilai Ma, Liye Zhao, Weijun Yao +3

Large Language Model (LLM) personalization aims to align model behaviors with individual user preferences. Existing methods often focus on isolated user histories, neglecting the e…

cs.CL2026

Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs

Wu Li, Yigeng Zhou, Zesheng Shi +3

While recent self-training approaches have reduced reliance on human-labeled data for aligning LLMs, they still face critical limitations: (i) sensitivity to synthetic data quality…

cs.CV2026

PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models

Jiahui Guang, Zexun Zhan, Zhenlin Xu +5

Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmarks rely on synthetic knowledge…

cs.AI2025

Unveiling Modality Bias: Automated Sample-Specific Analysis for Multimodal Misinformation Benchmarks

Hehai Lin, Hui Liu, Shilei Cao +3

Numerous multimodal misinformation benchmarks exhibit bias toward specific modalities, allowing detectors to make predictions based solely on one modality. While previous research…

cs.CL2025

STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment

Jiaqian Li, Qisheng Hu, Jing Li +1

In-Context Learning (ICL) has become a powerful paradigm that enables LLMs to perform a wide range of tasks without task-specific fine-tuning. However, the effectiveness of ICL hea…