ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
Paper • 2512.05111 • Published • 50 •
2
Shengyuan Ding
ChrisDing1105
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time upvoted a paper 7 days ago
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models liked a dataset 10 days ago
ibm-granite/ChartNetOrganizations
None yet
commented a
paper 4 months ago
commented a
paper about 1 year ago