-
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 • 27 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 28 • 2
Zhangchen Xu PRO
zhangchenxu
AI & ML interests
LLM Data, Alignment, Post-Training, Safety
Recent Activity
updated
a model
about 9 hours ago
zhangchenxu/Qwen2.5-14B-Instruct-SFT-LR1.0e-5-EPOCHS2-KimiK2-20250820_055153
updated
a model
about 9 hours ago
zhangchenxu/GLM-4-9B-0414-SFT-LR1.0e-5-EPOCHS2-OSS-20250820_060458_G4
updated
a model
about 10 hours ago
zhangchenxu/Qwen2.5-7B-Instruct-SFT-LR1.0e-5-EPOCHS2-OSS-20250820_055005_TB
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 • 27 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 28 • 2
models
49
zhangchenxu/Qwen2.5-14B-Instruct-SFT-LR1.0e-5-EPOCHS2-KimiK2-20250820_055153
0.0B
•
Updated
zhangchenxu/GLM-4-9B-0414-SFT-LR1.0e-5-EPOCHS2-OSS-20250820_060458_G4
0.0B
•
Updated
zhangchenxu/Qwen2.5-7B-Instruct-SFT-LR1.0e-5-EPOCHS2-OSS-20250820_055005_TB
0.0B
•
Updated
zhangchenxu/Qwen3-4B-Instruct-2507-SFT-LR1.0e-5-EPOCHS2-KimiK2-20250820_050810
0.0B
•
Updated
zhangchenxu/Qwen2.5-32B-Instruct-SFT-LR1.0e-5-EPOCHS2-Qwen3-20250820_053336
Updated
zhangchenxu/Qwen2.5-7B-Instruct-SFT-LR1.0e-5-EPOCHS2-KimiK2-20250820_053145
Updated
zhangchenxu/Qwen3-4B-Instruct-2507-SFT-LR1.0e-5-EPOCHS2-OSS-20250820_043244
0.0B
•
Updated
zhangchenxu/Qwen3-4B-Instruct-2507-SFT-LR1.0e-5-EPOCHS2-Qwen3-20250820_040103
0.0B
•
Updated
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step312
4B
•
Updated
•
16
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step288
4B
•
Updated
•
15
datasets
16
zhangchenxu/Qwen3_trajectory_1_filtered_converted
Viewer
•
Updated
•
23.5k
zhangchenxu/KimiK2_trajectory_1_filtered_converted
Viewer
•
Updated
•
22.4k
zhangchenxu/HardVerify-Math
Viewer
•
Updated
•
250
•
61
•
1
zhangchenxu/TinyV_Think_Training_Data_Qwen3_Balanced
Viewer
•
Updated
•
113k
•
4
zhangchenxu/TinyV_Training_Data_Qwen3_Balanced
Viewer
•
Updated
•
113k
•
4
zhangchenxu/bigmath_tinyv_filtered
Viewer
•
Updated
•
7.01k
•
21
zhangchenxu/TinyV_Training_Data_Balanced
Viewer
•
Updated
•
159k
•
12
zhangchenxu/TinyV_Think_Training_Data_Balanced
Viewer
•
Updated
•
159k
•
1
zhangchenxu/KodCode_50K_R1
Viewer
•
Updated
•
50k
•
16
zhangchenxu/KodCode_Hard_18K_R1
Viewer
•
Updated
•
18.7k
•
4