Pulkit Verma

Pulkit Verma
Arizona State University | ASU · School of Computing and Augmented Intelligence

M.Tech. Computer Science and Engineering

About

11
Publications
902
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
57
Citations
Introduction
My primary interests lie in AI safety, AI planning, action-model learning, and analysis of abstractions. My research focuses on the safe and reliable behavior of AI agents. I am currently investigating the minimal set of interfaces in an AI system that would enable a user to assess and understand the limits of its safe operability. In the past, I have worked in the area of speech processing, and the internet of things. My papers are available at https://pulkitverma.net/publications/
Additional affiliations
August 2018 - present
Arizona State University
Position
  • Research Assistant
July 2015 - July 2018
NetApp, Bengaluru, India
Position
  • Member of Technical Staff
August 2013 - May 2015
Indian Institute of Technology Guwahati
Position
  • Research Assistant

Publications

Publications (11)
Preprint
Much of the research on learning symbolic models of AI agents focuses on agents with stationary models. This assumption fails to hold in settings where the agent's capabilities may change as a result of learning, adaptation, or other post-deployment modifications. Efficient assessment of agents in such settings is critical for learning the true cap...
Preprint
This paper presents JEDAI, an AI system designed for outreach and educational efforts aimed at non-AI experts. JEDAI features a novel synthesis of research ideas from integrated task and motion planning and explainable AI. JEDAI helps users create high-level, intuitive plans while ensuring that they will be executable by the robot. It also provides...
Preprint
One of the several obstacles in the widespread use of AI systems is the lack of requirements of interpretability that can enable a layperson to ensure the safe and reliable behavior of such systems. We extend the analysis of an agent assessment module that lets an AI system execute high-level instruction sequences in simulators and answer the user...
Conference Paper
The vast diversity of internal designs of black-box AI systems and their nuanced zones of safe functionality make it difficult for a layperson to use them without unintended side effects. The focus of my dissertation is to develop algorithms and requirements of interpretability that would enable a user to assess and understand the limits of an AI s...
Preprint
Several approaches have been developed to answer specific questions that a user may have about an AI system that can plan and act. However, the problems of identifying which questions to ask and that of computing a user-interpretable symbolic description of the overall capabilities of the system have remained largely unaddressed. This paper present...
Preprint
This paper develops a new approach for estimating the internal model of an autonomous agent that can plan and act, by interrogating it. In this approach, the user may ask an autonomous agent a series of questions, which the agent answers truthfully. Our main contribution is an algorithm that generates an interrogation policy in the form of a sequen...
Article
In the domain of speech recognition many methods have been proposed over time like Gaussian mixture models (GMM), GMM with universal background model (GMM-UBM framework), joint factor analysis, etc. i-Vector subspace modeling is one of the recent methods that has become the state of the art technique in this domain. This method largely provides the...
Conference Paper
In a variety of problem domains, it has been observed that the aggregate opinions of groups are often more accurate than those of the constituent individuals, a phenomenon that has been termed the “wisdom of the crowd.” Yet, perhaps surprisingly, there is still little consensus on how generally the phenomenon holds, how best to aggregate crowd judg...
Conference Paper
Interaction with a robot has been an active area of research since the inception of robotics. Talking to a robot has always been considered the most natural way to communicate with it. But it is not always possible to have a full-fledged, standalone speech processing engine to be present on a robot or on a single machine. A dedicated system to conv...
Conference Paper
Modern-day devices like smart-phones, tablets, televisions etc. possess very powerful processors and huge storage capacities compared to what were available a few years ago. Most of these devices are also connected to the Internet. However, the full capabilities of these devices are not fully harnessed and thus, they are not as intelligent as they...

Network

Cited By