Make Theorem Proving Great Again!
Zhi Zhou
WNJXYK
AI & ML interests
Test-Time Adaptation, Test-Time Scaling, Test-Time Learning
Recent Activity
updated a model about 9 hours ago
WNJXYK/TTA-CIFAR-100-AugMix-WRN40 published a model about 9 hours ago
WNJXYK/TTA-CIFAR-100-AugMix-WRN40 updated a dataset about 15 hours ago
WNJXYK/TTA-CIFAR-100-COrganizations
-
Training-Free Group Relative Policy Optimization
Paper • 2510.08191 • Published • 46 -
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
Paper • 2510.15444 • Published • 151 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 48 -
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Paper • 2504.15785 • Published • 22
Make Theorem Proving Great Again!
-
Training-Free Group Relative Policy Optimization
Paper • 2510.08191 • Published • 46 -
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
Paper • 2510.15444 • Published • 151 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 48 -
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Paper • 2504.15785 • Published • 22
datasets 8
WNJXYK/TTA-CIFAR-10-C
Viewer • Updated • 750k • 10
WNJXYK/TTA-CIFAR-100-C
Viewer • Updated • 950k
WNJXYK/MATH-Reasoning-Paths
Updated • 93 • 30
WNJXYK/OlympiadBench-Reasoning-Paths
Updated • 85 • 16
WNJXYK/AIME_1983_2024-Reasoning-Paths
Updated • 231 • 16
WNJXYK/MathOdyssey-Reasoning-Paths
Updated • 110 • 20
WNJXYK/LawQA
Viewer • Updated • 96.7k • 28 • 14
WNJXYK/LawBench_Results
Preview • Updated • 7