-
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
published
a model
32 minutes ago
zhangchenxu/Qwen2.5-7B-Instruct-t2_25k_v2_tag4_processed
updated
a model
about 8 hours ago
zhangchenxu/Qwen2.5-14B-Instruct-OSS_1T_SFT-LR2.0e-5-EPOCHS2
updated
a model
about 9 hours 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
47
zhangchenxu/Qwen2.5-7B-Instruct-t2_25k_v2_tag4_processed
Updated
zhangchenxu/Qwen2.5-14B-Instruct-OSS_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
2
zhangchenxu/Qwen2.5-14B-Instruct-Qwen3_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
2
zhangchenxu/Qwen2.5-14B-Instruct-KimiK2_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
3
zhangchenxu/Qwen2.5-7B-Instruct-OSS_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
2
zhangchenxu/Qwen2.5-7B-Instruct-Qwen3_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
2
zhangchenxu/Qwen2.5-7B-Instruct-KimiK2_1T_SFT-LR2.0e-5-EPOCHS2
0.0B
•
Updated
•
2
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step312
4B
•
Updated
•
20
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step288
4B
•
Updated
•
19
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step256
4B
•
Updated
•
77
datasets
16
zhangchenxu/Qwen3_trajectory_1_filtered_converted
Viewer
•
Updated
•
23.5k
•
6
zhangchenxu/KimiK2_trajectory_1_filtered_converted
Viewer
•
Updated
•
22.4k
•
3
zhangchenxu/HardVerify-Math
Viewer
•
Updated
•
250
•
76
•
1
zhangchenxu/TinyV_Think_Training_Data_Qwen3_Balanced
Viewer
•
Updated
•
113k
•
3
zhangchenxu/TinyV_Training_Data_Qwen3_Balanced
Viewer
•
Updated
•
113k
•
5
zhangchenxu/bigmath_tinyv_filtered
Viewer
•
Updated
•
7.01k
•
29
zhangchenxu/TinyV_Training_Data_Balanced
Viewer
•
Updated
•
159k
•
14
zhangchenxu/TinyV_Think_Training_Data_Balanced
Viewer
•
Updated
•
159k
•
2
zhangchenxu/KodCode_50K_R1
Viewer
•
Updated
•
50k
•
16
zhangchenxu/KodCode_Hard_18K_R1
Viewer
•
Updated
•
18.7k
•
5