no code implementations • 7 Dec 2024 • Dillon Z. Chen, Pulkit Verma, Siddharth Srivastava, Michael Katz, Sylvie Thiébaux
Automated decision-making is a fundamental topic that spans multiple sub-disciplines in AI: reinforcement learning (RL), AI planning (AP), foundation models, and operations research, among others.
1 code implementation • 27 Mar 2024 • Rushang Karia, Daniel Bramblett, Daksh Dobhal, Pulkit Verma, Siddharth Srivastava
This paper presents $\forall$uto$\exists$val, a new approach for scaling LLM assessment in translating formal syntax -- such as first-order logic, regular expressions, etc -- to natural language (interpretation) or vice versa (compilation), thereby facilitating their use in applications such as generating/explaining logic and control flow for programs etc.
no code implementations • 19 Feb 2024 • Naman Shah, Jayesh Nagpal, Pulkit Verma, Siddharth Srivastava
Empirical results in deterministic settings show that powerful abstract representations can be learned from just a handful of robot trajectories; the learned relational representations include but go beyond classical, intuitive notions of high-level actions; and that the learned models allow planning algorithms to scale to tasks that were previously beyond the scope of planning without hand-crafted abstractions.
1 code implementation • 13 Feb 2024 • Rushang Karia, Pulkit Verma, Alberto Speranzon, Siddharth Srivastava
This paper introduces a new approach for continual planning and model learning in relational, non-stationary stochastic environments.
1 code implementation • 7 Jun 2023 • Pulkit Verma, Rushang Karia, Siddharth Srivastava
It is essential for users to understand what their AI systems can and can't do in order to use them safely.
10 code implementations • 16 Apr 2022 • Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Maitreya Patel, Kuntal Kumar Pal, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, Rushang Karia, Shailaja Keyur Sampat, Savan Doshi, Siddhartha Mishra, Sujan Reddy, Sumanta Patro, Tanay Dixit, Xudong Shen, Chitta Baral, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi, Daniel Khashabi
This large and diverse collection of tasks enables rigorous benchmarking of cross-task generalization under instructions -- training models to follow instructions on a subset of tasks and evaluating them on the remaining unseen ones.
1 code implementation • 24 Mar 2022 • Rashmeet Kaur Nayyar, Pulkit Verma, Siddharth Srivastava
In this work, we propose a novel approach to "differentially" assess black-box AI agents that have drifted from their previously known models.
1 code implementation • 31 Oct 2021 • Naman Shah, Pulkit Verma, Trevor Angle, Siddharth Srivastava
This paper presents JEDAI, an AI system designed for outreach and educational efforts aimed at non-AI experts.
no code implementations • 21 Aug 2021 • Pulkit Verma, Siddharth Srivastava
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.
1 code implementation • 28 Jul 2021 • Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava
Starting from a set of user-interpretable state properties, an AI agent, and a simulator that the agent can interact with, our algorithm returns a set of high-level capabilities with their parameterized descriptions.
1 code implementation • 29 Dec 2019 • Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava
This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act.