-
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Paper • 2503.06749 • Published • 31 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 138 -
OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
Paper • 2506.02397 • Published • 35
Rohit Saxena
rohitsaxena
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
10 days ago
Learning GUI Grounding with Spatial Reasoning from Visual Feedback
new activity
about 1 month ago
VLMEval/OpenVLMRecords:Records for new models
upvoted
a
paper
3 months ago
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of
Deep-Research Agent
Organizations
