← Amrit Singh Bedi

News

2026
Publication

Two papers accepted to ICLR 2026

Two papers from our group accepted to ICLR 2026 in Rio de Janeiro, Brazil.

2026
Publication

Paper accepted to EACL 2026

LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds

2026
Publication

Paper on safety of VLMs accepted to AAAI 2026

2025
Publication

Paper accepted to Nature Biotechnology

Our work on generative AI and biosecurity. Read →

2025
Publication

Three papers accepted to NeurIPS 2025

Work spanning reasoning models, theoretical RL, and LLM alignment. San Diego, CA.

2025
Publication

Paper accepted to EMNLP 2025

2025
Publication

Paper accepted to CDC 2025

2025
Publication

Three papers accepted to IROS 2025

2025
Publication

Paper accepted to ICML 2025

Vancouver, Canada.

2025
Publication

Paper accepted to IEEE RAL 2025

Multi-robot coordination via locality-based factorized multi-agent actor-critic.

2025
Publication

Paper accepted to CVPR 2025

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

2025
Workshop

Organizing the first NeurIPS Workshop on Biosecurity Safeguards for Generative AI

San Diego, California, USA.

2025
Talk

Invited talk at Asilomar 2025 on satisficing alignment

2025
Talk

Presented Transfer Q* at UT Austin

2025
Service

Area Chair — ACL 2025, NeurIPS 2025

2025
Service

Area Chair — Transactions on Machine Learning Research (TMLR)

2024
Publication

Two papers accepted to NeurIPS 2024

Vancouver, Canada.

2024
Publication

Five papers accepted to ICML 2024

Vienna, Austria. Including one Spotlight (top 3.5% of submissions).

2024
Publication

Three papers accepted to IROS 2024

Abu Dhabi, UAE.

2024
Publication

Paper accepted to ICLR 2024

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning

2024
Publication

Paper accepted to JMLR

On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control

2024
Publication

Paper accepted to TMLR

A Survey on the Possibilities & Impossibilities of AI-Generated Text Detection

2024
Talk

Invited talks at IBM Research, Google DeepMind NYC, and Amazon

Presented Transfer Q* and MaxMin-RLHF. Also presented at Amazon Rising Star Speaker Series (June 2024).

2024
Service

Area Chair — NeurIPS 2024

2023
Publication

Paper accepted (oral) at CoRL 2023

iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent RL — also won Best Paper at the Advances in Multi-Agent Learning Workshop at IROS 2023.

2023
Publication

Two papers accepted to ICML 2023

STEERING and Beyond Exponentially Fast Mixing in Average-Reward RL via Multi-Level Monte Carlo Actor-Critic.

2023
Publication

Three papers accepted to ICRA 2023

RTAW, Decentralized Multi-agent Exploration, and Heavy-Tailed Policy Optimization for sparse rewards.

2023
Publication

Two papers accepted (oral) to AAAI 2023

2023
Publication

Paper accepted to ICLR 2023

SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication

2023
Publication

Paper accepted to JAIR

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach

2023
Publication

Paper accepted to IEEE TAI

Regret and Belief Complexity Trade-off in Gaussian Process Bandits via Information Thresholding

2023
Service

Area Chair — NeurIPS 2023

2022
Publication

Two papers accepted to ICML 2022 (spotlight talks)

On the Hidden Biases of Policy Mirror Ascent; FedNew for federated learning.

2022
Publication

Two papers accepted to IROS 2022

Distributed Riemannian Optimization; DC-MRTA for multi-robot task allocation.

2022
Publication

Paper accepted to CoRL 2022

HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce.

2022
Publication

Paper accepted to IEEE TSP

Projection-Free Algorithm for Stochastic Bi-level Optimization.

2022
Publication

Two papers accepted to AAAI 2022

2022
Funding

Amazon Research Award 2022

For the proposal "Ensuring fairness via federated learning beyond consensus" at the University of Maryland.

2022
Funding

ARL Grant — Efficient Multi-Agent RL for Next-generation Team of Combat Vehicles

Principal Investigator.

2022
Funding

ARL Grant — Risk Sensitive Maneuver Tradeoffs for a Team of Ground Vehicles

Co-Principal Investigator.

2022
Funding

Northrop Grumman Seed Grant Award

Principal Investigator.