Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
Paper • 2604.08476 • Published • 8
Aditya Kanade
adi8196
·
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs submitted a paper about 1 month ago
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs submitted a paper about 1 month ago
Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMsOrganizations
upvoted a paper about 2 months ago
upvoted an article about 1 year ago
Article
Open-R1: a fully open reproduction of DeepSeek-R1
- +1
eliebak, lvwerra, lewtun
• • 889