AI safety researcher

Tsung-Yi Ho

Chinese University of Hong Kong

Google Scholar dblp OpenReview ORCID Homepage

Last 12 months3 papers

Interpretability 1

AI safety papers from the last year

On this site: 25 papers

May 2026

Safe Evolution with Circuit Anchors
May 24arXiv ↗

April 2026

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation
Apr 13arXiv ↗

February 2026

Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
Feb 3InterpretabilityarXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.