Article
12
Zhangchen Xu PRO
zhangchenxu
AI & ML interests
LLM Data, Alignment, Post-Training, Safety
Recent Activity
updated
a dataset about 11 hours ago
BakeAI/BakeAI_Reasoning_Math_L5_2603_Preview published
a dataset about 11 hours ago
BakeAI/BakeAI_Reasoning_Math_L5_2603_Preview updated
a dataset about 12 hours ago
BakeAI/BakeAI_Reasoning_Math_L4_2603_Preview Organizations
-
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Paper • 2505.14625 • Published • 13 -
TinyV
💬1Verify model answers against ground truth
-
zhangchenxu/TinyV-Qwen3-1.7B
Text Generation • 2B • Updated • 2 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 1 • 3
-
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Paper • 2505.14625 • Published • 13 -
TinyV
💬1Verify model answers against ground truth
-
zhangchenxu/TinyV-Qwen3-1.7B
Text Generation • 2B • Updated • 2 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 1 • 3
models 41
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step312
4B • Updated
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step288
4B • Updated
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step256
4B • Updated
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step224
4B • Updated
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step192
4B • Updated
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step160
4B • Updated
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step128
4B • Updated
• 1
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step96
4B • Updated
zhangchenxu/RB-Qwen2.5-VL-3B-Instruct-vlr_syn_filtered_10k_exp6_hybrid_nothink-GRPO_step64
4B • Updated
zhangchenxu/deepseek-math-7b-instruct-deepscaler_5k_prime_step468
7B • Updated
• 1
datasets 14
zhangchenxu/HardVerify-Math
Viewer
• Updated
• 250 • 155 • 2
zhangchenxu/TinyV_Think_Training_Data_Qwen3_Balanced
Viewer
• Updated
• 113k • 8
zhangchenxu/TinyV_Training_Data_Qwen3_Balanced
Viewer
• Updated
• 113k • 5
zhangchenxu/bigmath_tinyv_filtered
Viewer
• Updated
• 7.01k • 36
zhangchenxu/TinyV_Training_Data_Balanced
Viewer
• Updated
• 159k • 7
zhangchenxu/TinyV_Think_Training_Data_Balanced
Viewer
• Updated
• 159k • 5
zhangchenxu/KodCode_50K_R1
Viewer
• Updated
• 50k • 12
zhangchenxu/KodCode_Hard_18K_R1
Viewer
• Updated
• 18.7k • 8
zhangchenxu/Magpie-100k-Gemma2-9B
Viewer
• Updated
• 100k • 9
zhangchenxu/zero-eval
Viewer
• Updated
• 800 • 63