arXiv Machine Learning
Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
Oct 9
SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders
The paper introduces SAGE, a lightweight method that guides decoder attention in vision-language models away from prompt‑invariant attention sinks (PIS) toward query‑dependent regions of interest (ROIs). By using token‑aligned ROI masks from vision backbones like CLIP, ViT, and DINOv3, SAGE improves visual grounding and reduces hallucinations across various VLM families. Experiments show consistent gains on public vision‑language benchmarks, especially in fine‑grained visual discrimination tasks where localized evidence is essential.
arXiv Machine Learning
Jul 22
Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
arXiv:2607. 18615v1 Announce Type: cross Abstract: Machine unlearning for vision-language models (VLMs) remains underexplored.
Hugging Face Trending Papers
Jul 21
Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
Machine unlearning for vision-language models (VLMs) remains underexplored. Unlike language models, VLMs combine a language backbone with visual components, which makes unlearning more complex.
arXiv AI
4d ago
How Language Models Organize Task Information
arXiv:2610.27724v1 Announce Type: new Abstract: Dense linear probes assess task readability from language model (LM) representations, but do not directly reveal how many features suffice for predicti...
arXiv Computer Vision
Oct 12
In-Context Learning Can Help Vision-Language Models Overcome Training Priors
The paper shows that controlled visual in‑context learning can help vision‑language models (VLMs) overcome errors caused by training priors. By providing demonstrations, the models focus more on visual evidence, yielding significant accuracy gains on counterfactual examples while leaving prior‑aligned performance largely unchanged. This effect is observed across five VLM families and five vision‑centric tasks, indicating that many VLMs possess latent visual grounding abilities that standard tests may miss.
arXiv AI
Jun 2
VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
arXiv:2601. 03309v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities.