← Search

Jianghao Yin

2 accepted papers

2026

Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models

ICLR 2026poster

Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and visual perception capabilities predominantly engage different…

Cited by 4SourceScholar
2026

Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding

CVPR 2026

While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical in

Cited by 0SourceScholar