arXiv:2606. 23763v1 Announce Type: cross Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 20077v1 Announce Type: cross Abstract: Visual tokens enter Large Language Models (LLMs) as raw, foreign signals.
arXiv:2605. 20950v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference.
arXiv:2606. 03569v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference.
We find that vision-language models are sensitive to a specific semantically irrelevant change: the order in which the image and question are presented. Across three models and three benchmarks, image first prompting consistently outperforms question-first prompting, revealing a repeatable modality order failure.
arXiv:2607. 24017v1 Announce Type: cross Abstract: The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws.
Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predominantly rely on initial attention scores.