Across 19 multimodal LLMs, local Feynman-diagram recognition stays high while topological reconstruction and full amplitude derivation collapse.
Image tokens matter: Mitigating hallucination in discrete tokenizer-based large vision-language models via latent editing
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 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
-
FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
Across 19 multimodal LLMs, local Feynman-diagram recognition stays high while topological reconstruction and full amplitude derivation collapse.
-
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.