Zero-shot evaluation of open vision-language models as System 1 decision models on radiology tasks
cs.CV, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-14
Comments: 26 pages, 4 tables, 2 figures. v2: added Gemma 4 31B and MedGemma 1.5 4B to the comparison
Code: https://github.com/slowvak/System1Benchmark
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Value of System 1 Models in Medicine
- The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification
- Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs