collaborators

17 papers

cs.AI2026

Consilience: Conformally Calibrated Communication Control for Hidden-Profile Multi-Agent Reasoning

Abhijith Babu, Ramneet Kaur, Vishal Pramanik +7

Multi-agent LLM systems can improve reasoning by pooling diverse perspectives, but their effectiveness depends on coordinating communication, particularly in hidden-profile setting…

cs.AI2026

From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents

Trilok Padhi, Ramneet Kaur, Krishiv Agarwal +9

Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments. Despite their growing capabi…

cs.AI2026

Closed-Loop Neural Activation Control in Vision-Language-Action Models

Abhijith Babu, Ramneet Kaur, Nathaniel D. Bastian +5

Vision-Language-Action (VLA) models can be steered at test time by intervening on semantically meaningful internal directions, but existing methods use a fixed steering coefficient…

cs.LG2026

Do Diffusion Models Dream of Electric Planes? Discrete and Continuous Simulation-Based Inference for Aircraft Design

Aurelien Ghiglino, Daniel Elenius, Anirban Roy +7

In this paper, we generate conceptual engineering designs of electric vertical take-off and landing (eVTOL) aircraft. We follow the paradigm of simulation-based inference (SBI), wh…

cs.CR2026

Trojans in Artificial Intelligence (TrojAI) Final Report

Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68

The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…

cs.LG2026

Optimized Piecewise Affine Abstractions of Neural Networks with Learnable Activation Functions

Noah Schwartz, Chandra Kanth Nagesh, Sriram Sankaranarayanan +3

We present a generalized framework for the range verification of neural networks featuring non-linear activation functions. Our approach first constructs an ``optimized piecewise a…