# Systematic Evaluation of Large Vision-Language Models for Surgical Artificial Intelligence

arXiv: https://arxiv.org/abs/2504.02799 · HTML: https://mlsanity.com/paper/2504.02799/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 53 references that are in the map.
- First posted on arXiv 3 Apr 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos](https://mlsanity.com/paper/2109.03223/) (2021)
- [Surgical Data Science: Enabling Next-Generation Surgery](https://mlsanity.com/paper/1701.06482/) (2017)
- [ST-LLM: Large Language Models Are Effective Temporal Learners](https://mlsanity.com/paper/2404.00308/) (2024)
- [AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy](https://mlsanity.com/paper/2208.02049/) (2022)
- [TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models](https://mlsanity.com/paper/2410.23266/) (2024)
- [Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions](https://mlsanity.com/paper/2104.03829/) (2021)
- [Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures](https://mlsanity.com/paper/2307.15220/) (2023)
- [Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark](https://mlsanity.com/paper/2109.14956/) (2021)
- [SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge](https://mlsanity.com/paper/2401.00496/) (2023)
- [VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models](https://mlsanity.com/paper/2311.17404/) (2023)
- [Dissecting Self-Supervised Learning Methods for Surgical Computer Vision](https://mlsanity.com/paper/2207.00449/) (2022)
- [Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass Surgery](https://mlsanity.com/paper/2312.11250/) (2023)
- [Latent Graph Representations for Critical View of Safety Assessment](https://mlsanity.com/paper/2212.04155/) (2022)
- [RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations](https://mlsanity.com/paper/1802.03243/) (2018)

## Built on by (most cited first, 5 of 5)

- [SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning](https://mlsanity.com/paper/2603.06570/) (2026)
- [SurgXBench: Explainable Vision-Language Model Benchmark for Surgery](https://mlsanity.com/paper/2505.10764/) (2025)
- [SurgSigma: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence](https://mlsanity.com/paper/2603.16822/) (2026)
- [TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models](https://mlsanity.com/paper/2603.06999/) (2026)
- [A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling](https://mlsanity.com/paper/2603.27341/) (2026)

## Abstract (arXiv)

Large Vision-Language Models offer a new paradigm for AI-driven image understanding, enabling models to perform tasks without task-specific training. This flexibility holds particular promise across medicine, where expert-annotated data is scarce. Yet, VLMs' practical utility in intervention-focused domains--especially surgery, where decision-making is subjective and clinical scenarios are variable--remains uncertain. Here, we present a comprehensive analysis of 11 state-of-the-art VLMs across 17 key visual understanding tasks in surgical AI--from anatomy recognition to skill assessment--using 13 datasets spanning laparoscopic, robotic, and open procedures. In our experiments, VLMs demonstrate promising generalizability, at times outperforming supervised models when deployed outside their training setting. In-context learning, incorporating examples during testing, boosted performance up to three-fold, suggesting adaptability as a key strength. Still, tasks requiring spatial or temporal reasoning remained difficult. Beyond surgery, our findings offer insights into VLMs' potential for tackling complex and dynamic scenarios in clinical and broader real-world applications.