Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement Learning

Read full text Summarise with VIRAT
Authors: Jiajie Li, Chenhui Xu, Meihuan Liu, Jinjun Xiong
Cited by: 0
References: 33

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Conventional fine-tuning on domain-specific datasets can inadvertently alter a model's pretrained multimodal priors, leading to reduced generalization. To address this, we propose Chain-of-Adaptation (CoA), an adaptation framework designed to integrate domain knowledge while maintaining the model's inherent reasoning and perceptual capabilities. CoA introduces a structured reasoning format that enhances domain alignment without sacrificing general multimodal competence by reinforcement learning. Experiments on standard surgical benchmarks, under both in-distribution and out-of-distribution settings, demonstrate that CoA achieves higher accuracy, stronger generalization, and more stable behavior than supervised fine-tuning. Furthermore, ablation studies confirm that CoA effectively preserves the model's core visual-language abilities, providing a reliable pathway for domain specialization in VLMs.

Fields of Study & Subjects

Multimodal Machine Learning Applications Domain Adaptation and Few-Shot Learning Surgical Simulation and Training

Publication details

Journal / source
arXiv (Cornell University)
Publication date
20 March 2026
Language
EN
Document type
Preprint