ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
Paper
•
2512.05111
•
Published
•
40
MoonKuun
MoonKuun
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
F2LLM Technical Report: Matching SOTA Embedding Performance with 6
Million Open-Source Data
upvoted
a
paper
6 months ago
Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient
Attentions
Organizations
None yet
upvoted
a
paper
2 days ago
upvoted
a
paper
about 2 months ago
upvoted
3
papers
6 months ago
Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions
Paper
•
2410.06577
•
Published
•
14
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
Paper
•
2503.17793
•
Published
•
23
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
Paper
•
2505.16901
•
Published
•
48