SurgQ-VLM: Question-Conditioned Dual-Stream Compression and Answer-Type-Aware Reinforcement for Surgical Video Question Answering
cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/DhruvMakwana/SurgQ-VLM
Terminology
Sources
- Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
- Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery
- Qwen2.5-VL Technical Report
- SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding
- Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning
- PitVQA: Image-grounded Text Embedding LLM for Visual Question Answering in Pituitary Surgery
- Rethinking Generalization Performance of Surgical Phase Recognition with Expert-Generated Annotations
- Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models
- Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
- Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
- LLaVA-OneVision: Easy Visual Task Transfer
- LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning
- QG-VTC: Question-Guided Visual Token Compression in MLLMs for Efficient VQA
- Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
- Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
- Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
- MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
- Scalable Diffusion Models with Transformers
- Capabilities of Gemini Models in Medicine
- Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer
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