Research map / Video / Video generation
MedCache: Training-Free Spatially Aware Caching for Accelerated Medical Video Generation
Ufaq Khan, Umair Nawaz, Sathira Silva, Numan Saeed, Muhammad U Sheikh, Muhammad Bilal, Junaid Qadir, Lena Maier-Hein, Yutong Xie, Muhammad Haris Khan
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes MedCache, a training-free, spatially aware caching method to speed up inference of medical video generation models.
Problem
Inference cost of video world models adapted to medical applications (surgical simulation, procedural rehearsal, synthetic data generation) is a major obstacle; existing training-free caching methods trade off between lightweight global-change rules and more expensive approaches.
Approach
Training-free caching that is spatially aware, so that changes are tracked per region rather than only as an average change over the whole video, targeting the speed-quality trade-off of prior caching methods.
Closest papers by meaning
- Motion-Aware Caching for Efficient Autoregressive Video Generation (ICML 2026 · similarity 0.87)
- MagCache: Fast Video Generation with Magnitude-Aware Cache (NeurIPS 2025 · similarity 0.86)
- Accelerating Rectified Flow Models via Trajectory-Aware Caching (NeurIPS 2026 · similarity 0.86)
- FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality (ICLR 2025 · similarity 0.85)
- LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation (NeurIPS 2025 · similarity 0.85)
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
