MedSTP: Preserving Subspace and Transition Evidence for Medical VQA Token Pruning
arXiv:2610.22751v1 Announce Type: new Abstract: Medical vision-language models (VLMs) for visual question answering (VQA) often pass long visual-token sequences to the language model, making visual-token pruning attractive but risky for medical images, where answers may depend on localized boundary…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-19 04:00 · arXiv cs.CV
MedSTP: Preserving Subspace and Transition Evidence for Medical VQA Token Pruning