-
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 • 1 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 2 • 3
Zhangchen Xu PRO
zhangchenxu
AI & ML interests
LLM Data, Alignment, Post-Training, Safety
Recent Activity
updated a dataset 2 days ago
BakeAI/celeba-64-data published a dataset 2 days ago
BakeAI/celeba-64-data updated a dataset 2 days ago
BakeAI/celeba-64-fid-ref