Edward Suh

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)Recommendation & Information Retrieval (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Nanxi Li (1)Ying-Zi Ma (1)Yulong Cao (1)Bo Li (1)

Papers (1)

Sep 5, 2026

2w ago·also BAIR, NVIDIA

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

EvoSafeHarness is a safety-specific optimization framework that synthesizes a deployable harness for a frozen model in a target domain, guided by model behavior, domain specifications, and fresh-context adversarial review to reject benchmark-specific rules.

Nanxi Li, Ying-Zi Ma, Yulong Cao +5

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Recommendation & Information Retrieval+1

Search

Edward Suh

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)