Explanipedia

From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails Open

Ravi Pandya, Madison Bland, Duy P. Nguyen, Changliu Liu, Jaime Fernández Fisac , et al. · 2025

Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful cont…

A Unified Framework for Robots that Influence Humans over Long-Term Interaction Open

Shahabedin Sagheb, Sagar Parekh, Ravi Pandya, Ye-Ji Mun, Katherine Driggs-Campbell , et al. · 2025

Robot actions influence the decisions of nearby humans. Here influence refers to intentional change: robots influence humans when they shift the human's behavior in a way that helps the robot complete its task. Imagine an autonomous car tr…

Magnitude and dynamics of the T-cell response to SARS-CoV-2 infection at both individual and population levels Open

Thomas M. Snyder, Rachel M. Gittelman, Mark R. Klinger, Damon May, Edward J. Osborne , et al. · 2025

Introduction T cells are involved in the early identification and clearance of viral infections and also support the development of antibodies by B cells. This central role for T cells makes them a desirable target for assessing the immune…

Robots that Learn to Safely Influence via Prediction-Informed Reach-Avoid Dynamic Games Open

Ravi Pandya, Changliu Liu, Andrea Bajcsy · 2024

Robots can influence people to accomplish their tasks more efficiently: autonomous cars can inch forward at an intersection to pass through, and tabletop manipulators can go for an object on the table first. However, a robot's ability to i…

Robust Safe Control with Multi-Modal Dynamics Uncertainty Open

Tianhao Wei, Liqian Ma, Ravi Pandya, Changliu Liu · 2024

Multi-Agent Strategy Explanations for Human-Robot Collaboration Open

Ravi Pandya, Michelle Zhao, Changliu Liu, Reid Simmons, Henny Admoni · 2023

As robots are deployed in human spaces, it is important that they are able to coordinate their actions with the people around them. Part of such coordination involves ensuring that people have a good understanding of how a robot will act i…

Multimodal Safe Control for Human-Robot Interaction Open

Ravi Pandya, Tianhao Wei, Changliu Liu · 2023

Generating safe behaviors for autonomous systems is important as they continue to be deployed in the real world, especially around people. In this work, we focus on developing a novel safe controller for systems where there are multiple so…

Towards Proactive Safe Human-Robot Collaborations via Data-Efficient Conditional Behavior Prediction Open

Ravi Pandya, Zhuoyuan Wang, Yorie Nakahira, Changliu Liu · 2023

We focus on the problem of how we can enable a robot to collaborate seamlessly with a human partner, specifically in scenarios where preexisting data is sparse. Much prior work in human-robot collaboration uses observational models of huma…

Robust Safe Control with Multi-Modal Uncertainty Open

Tianhao Wei, Liqian Ma, Ravi Pandya, Changliu Liu · 2023

Safety in dynamic systems with prevalent uncertainties is crucial. Current robust safe controllers, designed primarily for uni-modal uncertainties, may be either overly conservative or unsafe when handling multi-modal uncertainties. To add…

Safe and Efficient Exploration of Human Models During Human-Robot Interaction Open

Ravi Pandya, Changliu Liu · 2022

Many collaborative human-robot tasks require the robot to stay safe and work efficiently around humans. Since the robot can only stay safe with respect to its own model of the human, we want the robot to learn a good model of the human in …

Fuzzy set intersection based paired-end short-read alignment Open

William J. Bolosky, Arun Subramaniyan, Matei Zaharia, Ravi Pandya, Taylor Sittler , et al. · 2021

Much genomic data comes in the form of paired-end reads: two reads that represent genetic material with a small gap between. We present a new algorithm for aligning both reads in a pair simultaneously by fuzzily intersecting the sets of ca…

Fuzzy set intersection based paired-end short-read alignment Open

William J. Bolosky, Arun Subramaniyan, Matei Zaharia, Ravi Pandya, Taylor Sittler , et al. · 2021

Much genomic data comes in the form of paired-end reads: two reads that represent genetic material with a small gap between. We present a new algorithm for aligning both reads in a pair simultaneously by fuzzily intersecting the sets of ca…

The Data Use Ontology to streamline responsible access to human biomedical datasets Open

Jonathan Lawson, Moran N. Cabili, Giselle Kerry, Tiffany Boughtwood, Adrian Thorogood , et al. · 2021

126. Magnitude and Dynamics of the T-Cell Response to SARS-CoV-2 Infection and Vaccination Open

Thomas M. Snyder, Rachel Gittelman, Mark Klinger, Damon May, Edward J. Osborne , et al. · 2021

Background T cells are central to the early identification and clearance of viral infections and support antibody generation by B cells, making them desirable for assessing the immune response to SARS-CoV-2 infection and vaccines. We combi…

Magnitude and Dynamics of the T-Cell Response to SARS-CoV-2 Infection at Both Individual and Population Levels Open

Thomas M. Snyder, Rachel M. Gittelman, Mark Klinger, Damon May, Edward J. Osborne , et al. · 2020

T cells are involved in the early identification and clearance of viral infections and also support the development of antibodies by B cells. This central role for T cells makes them a desirable target for assessing the immune response to …

Assembly of the 373k gene space of the polyploid sugarcane genome reveals reservoirs of functional diversity in the world's leading biomass crop Open

Gláucia Mendes Souza, Marie‐Anne Van Sluys, Carolina Gimiliani Lembke, Hayan Lee, Gabriel Rodrigues Alves Margarido , et al. · 2019

Background Sugarcane cultivars are polyploid interspecific hybrids of giant genomes, typically with 10–13 sets of chromosomes from 2 Saccharum species. The ploidy, hybridity, and size of the genome, estimated to have >10 Gb, pose a chal…

Nonverbal Robot Feedback for Human Teachers Open

Sandy H. Huang, Isabella Huang, Ravi Pandya, Anca D. Dragan · 2019

Robots can learn preferences from human demonstrations, but their success depends on how informative these demonstrations are. Being informative is unfortunately very challenging, because during teaching, people typically get no transparen…

Dhaka: variational autoencoder for unmasking tumor heterogeneity from single cell genomic data Open

Sabrina Mohd Rashid, Sohrab P. Shah, Ziv Bar‐Joseph, Ravi Pandya · 2019

Motivation Intra-tumor heterogeneity is one of the key confounding factors in deciphering tumor evolution. Malignant cells exhibit variations in their gene expression, copy numbers and mutation even when originating from a single progenito…

Human-AI Learning Performance in Multi-Armed Bandits Open

Ravi Pandya, Sandy H. Huang, Dylan Hadfield-Menell, Anca D. Dragan · 2019

People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at learning such tasks. Thus, there is an opportunity for AI a…

Registered access: authorizing data access Open

Stephanie O. M. Dyke, Mikael Lindén, Ilkka Lappalainen, Jordi Rambla, Knox Carey , et al. · 2018

Simplifying research access to genomics and health data with Library Cards Open

Moran N. Cabili, Knox Carey, Stephanie O. M. Dyke, Anthony J. Brookes, Marc Fiume , et al. · 2018

The volume of genomics and health data is growing rapidly, driven by sequencing for both research and clinical use. However, under current practices, the data is fragmented into many distinct datasets, and researchers must go through a sep…

Learning Image-Conditioned Dynamics Models for Control of Under-actuated\n Legged Millirobots Open

Anusha Nagabandi, Guangzhao Yang, Thomas Asmar, Ravi Pandya, Gregory Kahn , et al. · 2017

Millirobots are a promising robotic platform for many applications due to\ntheir small size and low manufacturing costs. Legged millirobots, in\nparticular, can provide increased mobility in complex environments and improved\nscaling of ob…

Learning Image-Conditioned Dynamics Models for Control of Under-actuated Legged Millirobots Open

Anusha Nagabandi, Guangzhao Yang, Thomas Asmar, Ravi Pandya, Gregory Kahn , et al. · 2017

Millirobots are a promising robotic platform for many applications due to their small size and low manufacturing costs. Legged millirobots, in particular, can provide increased mobility in complex environments and improved scaling of obsta…

Dhaka: Variational Autoencoder for Unmasking Tumor Heterogeneity from Single Cell Genomic Data Open

Sabrina Mohd Rashid, Sohrab P. Shah, Ziv Bar‐Joseph, Ravi Pandya · 2017

Motivation Intra-tumor heterogeneity is one of the key confounding factors in deciphering tumor evolution. Malignant cells exhibit variations in their gene expression, copy numbers, and mutation even when originating from a single progenit…

Molecularly targeted drug combinations demonstrate selective effectiveness for myeloid- and lymphoid-derived hematologic malignancies Open

Stephen E. Kurtz, Christopher A. Eide, Andy Kaempf, Vishesh Khanna, Samantha L. Savage , et al. · 2017

Significance Mononuclear cells obtained from freshly isolated patient samples with various hematologic malignancies were evaluated for sensitivities to combinations of drugs that target specific cell-signaling pathways. The diagnostic, gen…

Ravi Pandya YOU? Author Swipe