6 papers
Red-Teaming of Vision-Language-Action Models via Quality Diversity Environment Generation
Shihan Zhao, Henry Chen, Ya-Chuan Hsu +7
A long-standing goal in robotics is to develop generalist robots that can perform tasks across a wide range of settings, flexibly specified with images and text. Vision-Language-Ac…
Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies
Siddharth Srikanth, Freddie Liang, Ya-Chuan Hsu +9
Vision-Language-Action (VLA) models have significant potential to enable general-purpose robotic systems for a range of vision-language tasks. However, the performance of VLA-based…
Proactive Hardening of LLM Defenses with HASTE
Henry Chen, Victor Aranda, Samarth Keshari +2
Prompt-based attack techniques are one of the primary challenges in securely deploying and protecting LLM-based AI systems. LLM inputs are an unbounded, unstructured space. Consequ…
Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces
Bryon Tjanaka, Henry Chen, Matthew C. Fontaine +1
Quality diversity (QD) optimization searches for a collection of solutions that optimize an objective while attaining diverse outputs of a user-specified, vector-valued measure fun…
Persistent Homology-Guided Frequency Filtering for Image Compression
Anil Chintapalli, Peter Tenholder, Henry Chen +1
Feature extraction in noisy image datasets presents many challenges in model reliability. In this paper, we use the discrete Fourier transform in conjunction with persistent homolo…
Little Exploration is All You Need
Henry H. H. Chen, Jiaming Lu
The prevailing principle of "Optimism in the Face of Uncertainty" advocates for the incorporation of an exploration bonus, generally assumed to be proportional to the inverse squar…