conftrace_

lvlms

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

hallucinations (3) early layer activations (1) gpt-4v (1) image-grounded guidance (1) open-source vision models (1) logits subtraction (1) text inertia (1) object-level information (1) token logit (1) activation space (1)

Papers

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance ICML 2025 The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering ICML 2025 Paying More Attention to Images: A Training-Free Method for Alleviating Hallucination in LVLMs ECCV 2024