collaborators

6 papers

cs.CV2025

Revisiting KRISP: A Lightweight Reproduction and Analysis of Knowledge-Enhanced Vision-Language Models

Souradeep Dutta, Keshav Bulia, Neena S Nair

Facebook AI Research introduced KRISP [4], which integrates structured external knowledge into pipelines for vision-language reasoning. Despite its effectiveness, the original mode…

cs.RO2025

RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models

Kaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman +1

Multi-task ``vision-language-action'' (VLA) models have recently demonstrated increasing promise as generalist foundation models for robotics, achieving non-trivial performance out…

cs.LG2025

Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios

Vivian Lin, Ramneet Kaur, Yahan Yang +6

The safety of learning-enabled cyber-physical systems is compromised by the well-known vulnerabilities of deep neural networks to out-of-distribution (OOD) inputs. Existing literat…

cs.AI2025

Distributionally Robust Statistical Verification with Imprecise Neural Networks

Souradeep Dutta, Michele Caprio, Vivian Lin +5

A particularly challenging problem in AI safety is providing guarantees on the behavior of high-dimensional autonomous systems. Verification approaches centered around reachability…

cs.AI2025

REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments

Kaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman +1

Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the…

cs.LG2024

Credal Bayesian Deep Learning

Michele Caprio, Souradeep Dutta, Kuk Jin Jang +4

Uncertainty quantification and robustness to distribution shifts are important goals in machine learning and artificial intelligence. Although Bayesian Neural Networks (BNNs) allow…