#vision-language models
Vision-Language Models: 7 AI articles covering vision-language models news, analysis, and research
Articles
Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding forβ8
Liquid AI releases LFM2.5-VL-3B-DSpark, a speculative decoding drafter for its vision-language model, delivering up to 3.13x faster decoding on Apple silicon, w...
Feature Recovery for Object Understanding After Irreversibleβ7
TRACE benchmark and Feature Recovery Module improve post-fire object detection and identification when irreversible damage degrades vision model performance.
Evidence-Order Calibration for Selective Visual Reasoning underβ9
A lightweight reliability head with evidence-order supervision improves selective visual reasoning in VLMs, reducing monotonicity violations under progressive m...
FailSAE: Interpretable Failure Prediction for Vision-Languageβ9
Discover how sparse autoencoders enable interpretable failure prediction in vision-language models, revealing why errors occur for risk-aware AI decisions.
Taming Visual Neglect: A Variational Information Bottleneckβ9
New framework reveals when visual context helps or hurts multimodal in-context learning, with adaptive attention boosting accuracy by 4.7%.
Why We Fine-Tuned SigLIP (And When It Might Not Be the Right Choice)β10
How Alma Media fine-tuned SigLIP for multi-label real estate photo taggingβand when it might not be the right choice.
Can Vision-Language Models Assess Proxemic Risk from Egocentricβ10
Current VLMs show limits in egocentric proxemic risk assessment, though targeted prompts and fine-tuning boost high-danger recall in models like Qwen-VL.