1 citations · 1 across the 8 of their papers we have counts for
12 papers
Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction
Som Sagar, Shasha Li, Hejie Cui +2
Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Because the value of each desi…
PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation Models
Isaiah Milkey, Som Sagar, Aditya Taparia +3
Reliable video world models could provide scalable predictive environments for robot learning, planning, and evaluation. However, generated robot videos can violate physical princi…
Test-Time Adaptation of Manipulation Policies Under Actuator Degradation
Som Sagar, Ransalu Senanayake
Robot manipulation policies are usually trained under the assumption that a commanded action produces the same motion as it did during training even after hours of operation. Real…
Learning to Configure Agentic AI Systems
Aditya Taparia, Som Sagar, Ransalu Senanayake
Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts from a large combinatorial design space, and is typically handled today by fixed…
PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?
Atharva Gundawar, Som Sagar, Ransalu Senanayake
Vision-Language Models (VLMs) are increasingly pivotal for generalist robot manipulation, enabling tasks such as physical reasoning, policy generation, and failure detection. Howev…
Viewpoint-Agnostic Manipulation Policies with Strategic Vantage Selection
Sreevishakh Vasudevan, Som Sagar, Ransalu Senanayake
Since vision-based manipulation policies are typically trained from data gathered from a single viewpoint, their performance drops when the view changes during deployment. Naively…
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…