Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:LSCOLHTRrecord.jsonopen to challenge →
read the original abstract
Recent advancements in Surgical Visual Question Answering (Surgical-VQA) and related region grounding have shown great promise for robotic and medical applications, addressing the critical need for automated methods in personalized surgical mentorship. However, existing models primarily provide simple structured answers and struggle with complex scenarios due to their limited capability in recognizing long-range dependencies and aligning multimodal information. In this paper, we introduce Surgical-LVLM, a novel personalized large vision-language model tailored for complex surgical scenarios. Leveraging the pre-trained large vision-language model and specialized Visual Perception LoRA (VP-LoRA) blocks, our model excels in understanding complex visual-language tasks within surgical contexts. In addressing the visual grounding task, we propose the Token-Interaction (TIT) module, which strengthens the interaction between the grounding module and the language responses of the Large Visual Language Model (LVLM) after projecting them into the latent space. We demonstrate the effectiveness of Surgical-LVLM on several benchmarks, including EndoVis-17-VQLA, EndoVis-18-VQLA, and a newly introduced EndoVis Conversations dataset, which sets new performance standards. Our work contributes to advancing the field of automated surgical mentorship by providing a context-aware solution.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark
SurgCoT is a new benchmark that evaluates chain-of-thought spatiotemporal reasoning in multimodal large language models on surgical videos using five defined dimensions and an annotation protocol of Question-Option-Kn...
-
Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA
An RL framework uses digital twin representations with hierarchical uncertainty estimates and a novel clinical plausibility reward to train LLMs for surgical VideoQA, achieving SOTA on a new 2000-pair benchmark and tw...
-
LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models
LASER introduces curvature-weighted SVD from second-order loss approximation and loss-aware rank allocation to compress VLMs, reporting over 2.3x decoding speedup under low-precision settings.
-
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
DREAM-S combines neural architecture search, target-aware supernet training, and attention-entropy-guided distillation to accelerate speculative decoding in VLMs, reporting up to 3.85x speedup over standard methods.
-
Adapting 2D Multi-Modal Large Language Model for 3D CT Image Analysis
Transferring a 2D MLLM to 3D CT inputs via parameter reuse, a Text-Guided Hierarchical MoE framework, and two-stage training yields better performance than prior 3D medical MLLMs on medical report generation and visua...
-
Real-Time Multimodal Activity-Aware Error Detection in Robot-Assisted Surgery
Multimodal framework with activity prompting and kinematics integration improves error detection F1 by up to 5% on JIGSAWS and 16.6% on SAR-RARP50 over baselines.
-
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
A literature survey that unifies fragmented work on attacks, defenses, evaluations, and deployment challenges for Vision-Language-Action models in robotics.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.