Peizheng Guo — accepted AI-conference papers

2026

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs

Peizheng Guo, Jingyao Wang, Wenwen Qiang, Jiahuan Zhou, Changwen Zheng, Gang Hua

CVPR 2026

Despite Multimodal Large Language Models (MLLMs) having shown impressive capabilities, they may suffer from hallucinations. Empirically, we find that MLLMs attend disproportionately to task-irrelevant background regions compared with text-only LLMs, implying spurious background-answer correlations.

Cited by 0 Source ↗Scholar ↗

2026

Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration

Huijie Guo, Jingyao Wang, Peizheng Guo, Xingchen Shen, Changwen Zheng, Wenwen Qiang

AAAI 2026technical

In this paper, we explore the transferability of SSL by addressing two central questions: (i) what is the representation transferability of SSL, and (ii) how can we effectively model this transferability? Transferability is defined as the ability of a representation learned from one task to support

Cited by 0 Source ↗PDF ↗Scholar ↗