-
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 • 29 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 31 • 2
Zhangchen Xu PRO
zhangchenxu
AI & ML interests
LLM Data, Alignment, Post-Training, Safety
Recent Activity
liked
a dataset
4 days ago
Salesforce/APIGen-MT-5k
updated
a model
8 days ago
zhangchenxu/Qwen2.5-14B-Instruct-OSS_1T_SFT-LR2.0e-5-EPOCHS2
updated
a model
8 days ago
zhangchenxu/Qwen2.5-14B-Instruct-Qwen3_1T_SFT-LR2.0e-5-EPOCHS2
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 • 29 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 31 • 2
models
46
zhangchenxu/Qwen2.5-14B-Instruct-OSS_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
5
zhangchenxu/Qwen2.5-14B-Instruct-Qwen3_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
4
zhangchenxu/Qwen2.5-14B-Instruct-KimiK2_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
5
zhangchenxu/Qwen2.5-7B-Instruct-OSS_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
4
zhangchenxu/Qwen2.5-7B-Instruct-Qwen3_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
4
zhangchenxu/Qwen2.5-7B-Instruct-KimiK2_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
4
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step312
4B
•
Updated
•
21
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step288
4B
•
Updated
•
20
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step256
4B
•
Updated
•
77
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step224
4B
•
Updated
•
19
datasets
16
zhangchenxu/Qwen3_trajectory_1_filtered_converted
Viewer
•
Updated
•
23.5k
•
7
zhangchenxu/KimiK2_trajectory_1_filtered_converted
Viewer
•
Updated
•
22.4k
•
4
zhangchenxu/HardVerify-Math
Viewer
•
Updated
•
250
•
99
•
1
zhangchenxu/TinyV_Think_Training_Data_Qwen3_Balanced
Viewer
•
Updated
•
113k
•
5
zhangchenxu/TinyV_Training_Data_Qwen3_Balanced
Viewer
•
Updated
•
113k
•
8
zhangchenxu/bigmath_tinyv_filtered
Viewer
•
Updated
•
7.01k
•
70
zhangchenxu/TinyV_Training_Data_Balanced
Viewer
•
Updated
•
159k
•
19
zhangchenxu/TinyV_Think_Training_Data_Balanced
Viewer
•
Updated
•
159k
•
4
zhangchenxu/KodCode_50K_R1
Viewer
•
Updated
•
50k
•
8
zhangchenxu/KodCode_Hard_18K_R1
Viewer
•
Updated
•
18.7k
•
6