Minghui Jia
Maxwell-Jia
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
18 days ago
Group Sequence Policy Optimization
upvoted
a
paper
24 days ago
VisionThink: Smart and Efficient Vision Language Model via Reinforcement
Learning
updated
a collection
24 days ago
Daily arXiv
Organizations
-
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
Paper • 2411.14405 • Published • 62 -
Qwen/QwQ-32B-Preview
Text Generation • 33B • Updated • 68.8k • • 1.74k -
922
QwQ-32B-Preview
🔍QwQ-32B-Preview
-
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning
Paper • 2410.02884 • Published • 55
-
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
Paper • 2411.14405 • Published • 62 -
Qwen/QwQ-32B-Preview
Text Generation • 33B • Updated • 68.8k • • 1.74k -
922
QwQ-32B-Preview
🔍QwQ-32B-Preview
-
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning
Paper • 2410.02884 • Published • 55
datasets
6
Maxwell-Jia/gpqa-astro
Viewer
•
Updated
•
42
•
8
Maxwell-Jia/SuperGPQA-Astro
Viewer
•
Updated
•
405
•
11
Maxwell-Jia/AIME_2024
Viewer
•
Updated
•
30
•
14.9k
•
60
Maxwell-Jia/kepler_flare
Viewer
•
Updated
•
33.2k
•
24
•
2
Maxwell-Jia/MATH
Viewer
•
Updated
•
12.5k
•
111
•
3
Maxwell-Jia/astro-bench-test
Viewer
•
Updated
•
9.31k
•
7