1 citations · 1 across the 8 of their papers we have counts for
6 papers · 1 filter
RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields
Som Sagar, Jiafei Duan, Sreevishakh Vasudevan +4
Robot manipulation policies, while central to the promise of physical AI, are highly vulnerable in the presence of external variations in the real world. Diagnosing these vulnerabi…
ExpressivityBench: Can LLMs Communicate Implicitly?
Joshua Tint, Som Sagar, Aditya Taparia +4
Human communication is often implicit, conveying tone, identity, and intent beyond literal meanings. While large language models have achieved strong performance on explicit tasks…
LLM-Assisted Red Teaming of Diffusion Models through "Failures Are Fated, But Can Be Faded"
Som Sagar, Aditya Taparia, Ransalu Senanayake
In large deep neural networks that seem to perform surprisingly well on many tasks, we also observe a few failures related to accuracy, social biases, and alignment with human valu…
BaTCAVe: Trustworthy Explanations for Robot Behaviors
Som Sagar, Aditya Taparia, Harsh Mankodiya +3
Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the…
Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
Aditya Taparia, Som Sagar, Ransalu Senanayake
Understanding the inner representation of a neural network helps users improve models. Concept-based methods have become a popular choice for explaining deep neural networks post-h…
Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models
Som Sagar, Aditya Taparia, Ransalu Senanayake
In large deep neural networks that seem to perform surprisingly well on many tasks, we also observe a few failures related to accuracy, social biases, and alignment with human valu…