-
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Paper • 2505.14625 • Published • 13 -
1
TinyV
💬Verify model answers against ground truth
-
zhangchenxu/TinyV-Qwen3-1.7B
Text Generation • 2B • Updated • 38 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 33 • 1
Zhangchen Xu PRO
zhangchenxu
AI & ML interests
LLM Data, Alignment, Post-Training, Safety
Recent Activity
liked
a model
4 days ago
mistralai/Mistral-Small-3.2-24B-Instruct-2506
updated
a dataset
5 days ago
zhangchenxu/HardVerify-Math
updated
a collection
5 days ago
TinyV
Organizations
-
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Paper • 2505.14625 • Published • 13 -
1
TinyV
💬Verify model answers against ground truth
-
zhangchenxu/TinyV-Qwen3-1.7B
Text Generation • 2B • Updated • 38 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 33 • 1
models
7
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation
•
2B
•
Updated
•
33
•
1
zhangchenxu/TinyV-Qwen3-1.7B
Text Generation
•
2B
•
Updated
•
38
zhangchenxu/TinyV-1.5B-Think
Text Generation
•
2B
•
Updated
•
70
zhangchenxu/TinyV-1.5B
Text Generation
•
2B
•
Updated
•
1.95k
•
1
zhangchenxu/gemma-2-2b-magpie-gemma2-9b-flash
Text Generation
•
3B
•
Updated
•
18
zhangchenxu/Llama-2-7b-Alpaca52k-GPT4
Text Generation
•
7B
•
Updated
•
17
zhangchenxu/Llama-2-7b-Alpaca52k
Text Generation
•
7B
•
Updated
•
45
datasets
14
zhangchenxu/HardVerify-Math
Viewer
•
Updated
•
250
•
173
•
1
zhangchenxu/TinyV_Think_Training_Data_Qwen3_Balanced
Viewer
•
Updated
•
113k
•
1
zhangchenxu/TinyV_Training_Data_Qwen3_Balanced
Viewer
•
Updated
•
113k
•
1
zhangchenxu/bigmath_tinyv_filtered
Viewer
•
Updated
•
7.01k
•
74
zhangchenxu/TinyV_Training_Data_Balanced
Viewer
•
Updated
•
159k
•
14
zhangchenxu/TinyV_Think_Training_Data_Balanced
Viewer
•
Updated
•
159k
•
55
zhangchenxu/KodCode_50K_R1
Viewer
•
Updated
•
50k
•
47
zhangchenxu/KodCode_Hard_18K_R1
Viewer
•
Updated
•
18.7k
•
43
zhangchenxu/Magpie-100k-Gemma2-9B
Viewer
•
Updated
•
100k
•
33
zhangchenxu/zero-eval
Viewer
•
Updated
•
800
•
115