Duncan Eddy — accepted AI-conference papers

2026

Foundational World Models Accurately Detect Bimanual Manipulator Failures

Isaac Ronald Ward, Michelle Ho, Houjun Liu, Aaron Feldman, Joseph Vincent, Liam Kruse +4

ICRA 2026poster

It is currently challenging to deploy visuomotor robots at scale due to the potential of anomalous failures degrading performance, causing damage, or endangering human life. Bimanual manipulators are no exception; these robots have vast state spaces comprised of high-dimensional images and proprioce…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts

Amelia Hardy, Houjun Liu, Allie Griffith, Bernard Lange, Duncan Eddy, Mykel Kochenderfer

EMNLP 2025

Existing LLM red-teaming approaches prioritize high attack success rate, often resulting in high-perplexity prompts. This focus overlooks low-perplexity attacks that are more difficult to filter, more likely to arise during benign usage, and more impactful as negative downstream training examples. I

Cited by 0 Source ↗PDF ↗Scholar ↗