2026
REVIS: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
ICML 2026poster
Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper network layers. To address this, we propose REVIS, a training-…