Back to papers
April 9, 2026cs.CVcs.AI

Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization

Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha, Vineeth N Balasubramanian, Tanuja Ganu
Read on arXivDownload PDF
HF Upvotes

6

Categories

cs.CV, cs.AI