AI safety researcher

Ding Zhao

Google Scholar dblp ORCID

Last 12 months2 papers

Evaluation and benchmarks 1

AI safety papers from the last year

On this site: 21 papers

October 2026

Controllable and Photorealistic Pedestrian Risky Motion Generation for End-to-End Driving Safety Evaluation
Oct 5Evaluation and benchmarksarXiv ↗

September 2026

SAGE: Safety-Aligned Gradient Enforcement for Human--Robot Collaboration
Sep 17arXiv ↗

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