Yingxuan Zhuang

Mitigating Manifold Departure: Uncertainty-aware Subspace Rectification for Trustworthy MLLM Decoding

Multimodal Large Language Models often suffer from object hallucinations, where generated outputs are inconsistent with the visual evidence. This issue is typically attributed to the over-reliance on language priors, which can override the visual context. Recent training-free decoding strategies add…