Layer-wise Laplacian energy of visual attention reveals hallucination emergence in MLLMs and enables LaSCD, a closed-form logit remapping strategy that mitigates hallucinations while preserving general performance.
MLLM can see? dynamic correction decoding for hallucination mitigation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
Visual latents in MLLMs are systematically silenced by autoregressive training but can be unsilenced at inference via query-guided contrastive alignment followed by a confidence-progression reward.
citing papers explorer
-
When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
Layer-wise Laplacian energy of visual attention reveals hallucination emergence in MLLMs and enables LaSCD, a closed-form logit remapping strategy that mitigates hallucinations while preserving general performance.
-
Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
Visual latents in MLLMs are systematically silenced by autoregressive training but can be unsilenced at inference via query-guided contrastive alignment followed by a confidence-progression reward.