SAM Meets VLM: Parameter-Decoupled Full-Parameter Training for Unified Medical Reasoning and Segmentation

arXiv:2609.37283 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Benchmark — 23× in this paper · explained in 2 episodes
• Grounding — 22× in this paper · explained in 3 episodes
• Instruction Tuning — 10× in this paper · explained in 2 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Alignment — 7× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Adaptation — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Foundation Model — 4× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Knowledge graphs — 1× in this paper · explained in 2 episodes
• Mask Generation — 1× in this paper · explained in 2 episodes
• Multi-objective Optimization — 1× in this paper · explained in 4 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats
• ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models
• HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs
• HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
• HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
• Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
• Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine
• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
• ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge
• PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
• Improved Baselines with Visual Instruction Tuning
• SAM 2: Segment Anything in Images and Videos
• A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge
• MedGemma Technical Report
• MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization
• Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support
• Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning
• MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models