Find a story

Search Spins

Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.

5 results for “vision-language models”

SPIN Processed News Frame: The Hype

Jako Tako or Fluent? Presenting PoVisLE: A Polish Vision-Language Evaluation

Researchers introduced PoVisLE, a Polish-specific vision-language benchmark with 1,117 images and 2,366 VQA pairs, designed to evaluate culturally grounded multimodal understanding beyond surface-level recognition.

Spin 65% Claim Present in Source AI Risk Moderate
arXiv Computation and Language

Aug 11, 2026

SPIN Processed News Frame: The Hype

CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models

Researchers introduced CARPRT, a class-aware prompt reweighting method for zero-shot image classification with black-box vision-language models, improving accuracy by modeling prompt-class dependencies without requiring model training or fine-tuning.

Spin 40% Claim Present in Source AI Risk Moderate
arXiv Machine Learning

Jul 18, 2026

SPIN Processed News Frame: The Hype

Reward Valuation in Vision Language Models: Causal Mechanisms Underlying Anhedonia

Researchers use clinical neuroscience methods to identify and causally test reward-anticipatory units in vision-language models, finding perturbations induce anhedonia-like behavioral shifts without impairing core task performance.

Spin 75% Claim Present in Source AI Risk High
arXiv Machine Learning

Jul 10, 2026

SPIN Processed News Frame: The Hype

Evaluation of Multilingual Ability to Use Spatial Deictic Expressions in Vision-Language Models

Researchers introduced a new multilingual benchmark to evaluate how vision-language models handle spatial deictic expressions (e.g., 'this'/'that') across four languages, finding consistent divergence from human usage patterns in distance-based demonstrative selection.

Spin 40% Claim Present in Source AI Risk Moderate
arXiv Computation and Language

Jul 10, 2026

SPIN Processed News Frame: The Hype

Does AI Understand Imaging? A Systematic Benchmark of Agentic AI for Computational Imaging Tasks

Researchers introduced ImagingBench, a new benchmark testing whether agentic AI systems can solve physics-based computational imaging tasks — revealing consistent underperformance versus task-specific non-agentic methods, especially in inverse and sensing problems.

Spin 45% Claim Present in Source AI Risk Moderate
arXiv Artificial Intelligence

Jul 10, 2026