Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers (https://arxiv.org/abs/2509.23152)
Zhicheng YANG
yangzhch6
AI & ML interests
reasoning with LLMs
Recent Activity
updated
a model
1 day ago
yangzhch6/Mirror-Verifier-1.5B
updated
a model
1 day ago
yangzhch6/Mirror-Verifier-7B
updated
a model
1 day ago
yangzhch6/Zero-Solver-Qwen2.5-Math-7B-L
Organizations
None yet
models
25
yangzhch6/Mirror-Verifier-1.5B
2B
•
Updated
yangzhch6/Mirror-Verifier-7B
8B
•
Updated
yangzhch6/Zero-Solver-Qwen2.5-Math-7B-L
8B
•
Updated
yangzhch6/Zero-Solver-Qwen2.5-Math-1.5B-L
2B
•
Updated
yangzhch6/Qwen2.5-Math-7B-L
Text Generation
•
8B
•
Updated
•
10
yangzhch6/Qwen2.5-7B-openr1-nothink-3k-f3
Updated
yangzhch6/Qwen2.5-1.5B-openr1-nothink-3k-f3
Updated
yangzhch6/mix-rlvr-verify
Updated
yangzhch6/DARS-Llama-HW-Breadth
8B
•
Updated
•
2
yangzhch6/Qwen2.5-Math-7B-L-openr1-nothink-3k-f3-step100
8B
•
Updated
•
7
datasets
5
yangzhch6/Mirror-Critique
Viewer
•
Updated
•
62.7k
yangzhch6/Qwen2.5-Math-7B-L-openr1-nothink-3k-f3-step500
Viewer
•
Updated
•
504
•
164
yangzhch6/Qwen2.5-Math-1.5B-L-openr1-nothink-3k-f3-step500
Viewer
•
Updated
•
504
•
192
yangzhch6/DARS-Dataset
Viewer
•
Updated
•
1.56k
•
39
yangzhch6/cuda12.4
Updated
•
15