SurgTransfer: Multi-Step Latent Action Modeling for Action Transfer in Surgical World Model
cs.CV, cs.AI, cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/bhattarailab/Surgical-Vision-World-Model
Terminology
Sources
- Cosmos World Foundation Model Platform for Physical AI
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment
- AdaWorld: Learning Adaptable World Models with Latent Actions
- Auto-Encoding Variational Bayes
- A Comprehensive Survey on World Models for Embodied AI
- World Models for General Surgical Grasping
- Visuomotor Grasping with World Models for Surgical Robots
- A Survey: Learning Embodied Intelligence from Physical Simulators and World Models
- Learning to Act without Actions
- Towards Suturing World Models: Learning Predictive Models for Robotic Surgical Tasks
- Towards Accurate Generative Models of Video: A New Metric & Challenges
- Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
- Latent Action Pretraining from Videos
- Cosmos-Surg-dVRK: World Foundation Model-based Automated Online Evaluation of Surgical Robot Policy Learning
- Intuitive Surgical SurgToolLoc and SurgVU Challenges Results: 2022-2025
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