arXiv Machine Learning July 27, 2026 By M M Asif Ferdous

Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

Read the original on arXiv Machine Learning →

arXiv:2607. 22034v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 28

Bigger or Cheaper? Scale and Quantization Effects on Uncertainty Signals in Vision-Language Models Under Image Degradation

arXiv:2607. 24440v1 Announce Type: cross Abstract: Vision-language models (VLMs) deployed on consumer hardware must decide when to answer and when to defer, and that decision depends on having a confidence signal that tracks correctness.

By M M Asif Ferdous

llms efficiency multimodal

arXiv AI

5d ago

How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures

arXiv:2608. 13267v1 Announce Type: cross Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with limited attention to behavioral reliability under uncertainty (how they behave when visual evidence is missing or misleading).

By Paul Osemudiame Oamen, Owusu-Banahene Osei, Ananya Mukherjee, Christian Greisinger, Steffen Eger, Pius Onobhayedo, Wei Zhao

llms multimodal benchmarks safety

arXiv Machine Learning

Aug 12

Predictive Entropy as a Joint Screen for Error and Paraphrase Instability in Medical Vision-Language Models

arXiv:2604. 08941v2 Announce Type: replace Abstract: Medical Vision-Language Models (VLMs) answering binary presence questions on chest radiographs can fail in two linked ways: they are confidently wrong, and they change answers when a clinically equivalent question is rephrased.

By Binesh Sadanandan, Vahid Behzadan

llms multimodal

arXiv AI

Jun 30

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift

arXiv:2606. 29699v1 Announce Type: cross Abstract: Vision Language Action models combine perception, language grounding, and control in a single policy, but their failures are hard to diagnose once visual conditions shift.

By Dipesh Tharu Mahato, Rachel Ren

robotics benchmarks

arXiv AI

Jul 10

When Thinking Hurts: Epistemic Signals in the Reasoning Chains of Visual Language Models

arXiv:2607. 08059v1 Announce Type: cross Abstract: Uncertainty quantification for visual language models (VLMs) conventionally targets the answer token distribution.

By Mayank Singal

llms safety

arXiv AI

Jun 17

Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Models

arXiv:2606. 17389v1 Announce Type: cross Abstract: Multimodal Foundation Models are increasingly used as reasoning agents, making reliability, knowing when a model may hallucinate, critical.

By Logan Mann, Yi Xia, Ajit Saravanan, Ishan Dave, Saadullah Ismail, Shikhar Shiromani, Emily Huang, Ruizhe Li, Kevin Zhu

llms agents multimodal

Related stories

Bigger or Cheaper? Scale and Quantization Effects on Uncertainty Signals in Vision-Language Models Under Image Degradation

How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures

Predictive Entropy as a Joint Screen for Error and Paraphrase Instability in Medical Vision-Language Models

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift

When Thinking Hurts: Epistemic Signals in the Reasoning Chains of Visual Language Models

Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Models