Junxiao Yang's picture

Junxiao Yang

yangjunxiao2021

·

https://yangjunx21.github.io/

yangjunx21

AI & ML interests

Alignment/AI safety

Recent Activity

upvoted a paper 4 days ago

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

authored a paper about 1 month ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

upvoted a paper about 1 month ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

View all activity

Organizations

commented 2 papers 8 months ago

Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

Paper • 2509.05739 • Published Sep 6, 2025 • 2 •

SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

Paper • 2509.07968 • Published Sep 9, 2025 • 14 •

New activity in openai/gpt-oss-120b 9 months ago

ImportError: /lib64/libc.so.6: version `GLIBC_2.32' not found

#86 opened 9 months ago by

commented a paper 12 months ago

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

Paper • 2505.13529 • Published May 18, 2025 • 11 •

New activity in thu-coai/AISafetyLab_Datasets over 1 year ago

Update README.md

#3 opened over 1 year ago by

yangjunxiao2021