-
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 • 5 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 6 • 3
Zhangchen Xu PRO
zhangchenxu
AI & ML interests
LLM Data, Alignment, Post-Training, Safety
Recent Activity
authored a paper 9 days ago
SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge authored a paper 9 days ago
Building a Foundational Guardrail for General Agentic Systems via
Synthetic Data authored a paper 9 days ago
PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic MemoryOrganizations
-
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 • 5 -
zhangchenxu/TinyV-Qwen3-1.7B-Think
Text Generation • 2B • Updated • 6 • 3