works on
hash-based summarization 1hyperloglog sketches 1long-context language models 1prompt reasoning 1set aggregation 1

From the 1 of 19 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning

Meng Lu, Yuxing Lu, Yuchen Zhuang +6

Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning t…