Visiting researcher
Stanford University
August 2023 - Present
Research scientist
JPMorgan AI Research
July 2023 - Present
Graduate student
Princeton University
September 2017 - May 2023
Research scientist intern
Deepmind
May 2022 - September 2022
Research scientist intern
FAIR
May 2021 - August 2021
Summer research intern
Siemens
May 2020 -
August 2020
News
Recent Projects
Work in Progress
➟
I am co-organizing a Proceedings of National Academy of Science (PNAS) special issue on "Collective Artificial Intelligence"
➟
Agentyx: A Framework for Building LLM Based Multi-agent Systems
➟
A Holistic Approach for Evaluating Agentic Systems
➟
Weak to Strong Generalization
➟
Enhanced Embodied Intelligence Through Multimodal Foundation Model Based Agents.
Generative AI: Social and resposible generative AI (2022-present)
☞
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
under review at ICLR 2025
☞
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
under review at ICLR 2025
☞
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
Safe Generative AI workshop at NeurIPS 2024
under review at ICLR 2025
☞
Policy Dreamer: Diverse Public Policy Generation Via Elicitation and Simulation of Human Preferences
Socially Responsible Language Modelling Research workshop at NeurIPS 2024
☞
Generative AI Agents for Knowledge Work Augmentation in Finance
accepted at Annual Reviews 2024
☞
Can LLMs be Scammed? A Baseline Measurement Study
Project-page / Pdf / Bibtex
☞
In-Context Learning with Topological Information for LLM-Based Knowledge Graph Completion
SPIGM workshop at ICML 2024
☞
O3D: Offline Data-Driven Discovery and Distillation for Sequential Decision Making with Large Language Models
COLM 2024
FMDM workshop at NeurIPS 2023
Project-page / Pdf / Bibtex
☞
SORRY-Bench: A Systematic Evaluation on Large Language Model Safety Refusal Behaviors
under review at NeurIPS 2024
Project-page / Pdf / Bibtex
☞
AI Risk Management Should Understand and Account for Both Safety and Security
under review 2024
Project-page / Pdf / Bibtex
Multi-agent Learning: Social intelligence in multi-agent RL (2015-present)
☞
Autocratic Learning and Unilateral Incentive Alignment in Two-player Stochastic Games
Accepted at PNAS 2024
Project-page / Pdf / Bibtex
☞
Zero-shot generalization: We develop methods that allow agents to successfully interact with novel partners during test time in mixed motive games.
☞
Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas
AAMAS 2023
Project-page / Pdf / Bibtex
Effective communication: We study how agents can minimize communication cost by deciding when and what to communicate depending on the sequence of options they chose.
☞
One More Step Towards Reality: Cooperative Bandits with Imperfect Communication
NuerIPS 2021
Project-page / Pdf / Bibtex
☞
Distributed Bandits: Probabilistic Communication on \(d\)-regular Graphs
ECC 2021
Project-page / Pdf / Bibtex
We analyze how agent-based strategies contribute to minimizing group regret under communication failures
☞
Distributed Learning: Sequential Decision Making in Resource-Constrained Environments
PML4DC workshop, ICLR 2020
Project-page / Pdf / Bibtex/ Slides
We design a partial communication protocol that obtains the same order of performance as full communication for a significantly smaller communication cost.
☞
A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem
ECC, 2020
Project-page / Pdf / Bibtex / Slides / Video
We propose a new communication protocol for multi-agent multi-armed bandit problem that improves group performance with only a logarithmic communication cost.
☞
Heterogeneous Explore-Exploit Strategies on Multi-Star Networks
IEEE Control Systems Letters, 2020
Project-page / Pdf / Bibtex
For distributed bandits with a multi-star communication graph, we show how sampling rules for center agents that favor exploring over exploiting make the information that center agents broadcast to their neighbors more useful and improve group performance.
☞
Heterogeneous Stochastic Interactions for Multiple Agents in a Multi-armed Bandit Problem
ECC, 2019
Project-page / Pdf / Bibtex / Slides
We consider the case where each agent observes all its neighbors independently with the same probability. We show that the performance of each agent depends on observation probabilities of its own and its neighbors.
Embodied AI: Human-robot coordination, control and planning (2015-present)
☞
Multi-robot Learning and Coverage of Unknown Spatial Fields
MRS, 2021
Project-page / Pdf / Bibtex / Slides / Video
We propose a novel explore-exploit based method for coverage in unknown special fields.
☞
Feedback Regularization and Geometric PID Control for Robust Stabilization of a Planar Three-link Hybrid Bipedal Walking Model
ACC, 2018
Project-page / Pdf / Bibtex / Slides / Video
We propose a geometric PID controller to stabilize a three-link planar bipedal hybrid dynamic walking robot.
☞
Semi-globally Exponential Trajectory Tracking for a Class of Spherical Robots
Automatica, 2017
Project-page / Pdf / Bibtex
We propose a geometric feedback controller for spherical robots capable of tracking a desired position on an inclined plane, in the presence of parameter uncertainty and uncertainty of the inclination of the rolling surface.
☞
Feedback Regularization and Geometric PID Control for Trajectory Tracking of Mechanical Systems: Hoop Robots on an Inclined Plane
ACC, 2017
Project-page / Pdf / Bibtex / Slides
We propose a geometric control strategy for semi-almost global output tracking for a class of interconnected under actuated mechanical systems.
Deep RL: Importance-sampling for data-efficient RL (2020-2022)
☞
On Using Hamiltonian Monte Carlo Sampling for Reinforcement Learning Problems in High-dimension
CDC 2022
Project-page / Pdf / Bibtex
We propose a data efficient modification of the \(Q\)-learning approach which uses Hamiltonian Monte Carlo to compute \(Q\) function for problems with stochastic, high-dimensional dynamics.
Teaching
I work as an assistant-in-teaching at Princeton University.