Make Theorem Proving Great Again!
Zhi Zhou
WNJXYK
AI & ML interests
Test-Time Adaptation, Test-Time Scaling, Test-Time Learning
Recent Activity
updated
a Space
about 17 hours ago
WNJXYK/dev
published
a Space
about 18 hours ago
WNJXYK/dev
updated
a collection
about 1 month ago
📝 [Paper List] Test-Time Learning for LLMs
Organizations
-
Training-Free Group Relative Policy Optimization
Paper • 2510.08191 • Published • 44 -
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
Paper • 2510.15444 • Published • 146 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 47 -
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Paper • 2504.15785 • Published • 21
Make Theorem Proving Great Again!
-
Training-Free Group Relative Policy Optimization
Paper • 2510.08191 • Published • 44 -
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
Paper • 2510.15444 • Published • 146 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 47 -
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Paper • 2504.15785 • Published • 21
datasets
6
WNJXYK/MATH-Reasoning-Paths
Updated
•
378
•
30
WNJXYK/OlympiadBench-Reasoning-Paths
Updated
•
833
•
16
WNJXYK/AIME_1983_2024-Reasoning-Paths
Updated
•
311
•
16
WNJXYK/MathOdyssey-Reasoning-Paths
Updated
•
142
•
20
WNJXYK/LawQA
Viewer
•
Updated
•
96.7k
•
58
•
14
WNJXYK/LawBench_Results
Preview
•
Updated
•
19