J Swaroop Guntupalli — accepted AI-conference papers

2025

Distributional Diffusion Models with Scoring Rules

Valentin De Bortoli, Alexandre Galashov, J Swaroop Guntupalli, Guangyao Zhou, Kevin Patrick Murphy, Arthur Gretton +1

ICML 2025poster

Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted. The corresponding reverse process progressively ``denoises" a Gaussian sample into a sample from the data distribution…

Cited by 3 Source ↗PDF ↗Scholar ↗

2025

Improving Transformer World Models for Data-Efficient RL

Antoine Dedieu, Joseph Ortiz, Xinghua Lou, Carter Wendelken, J Swaroop Guntupalli, Wolfgang Lehrach +2

ICML 2025poster

We present an approach to model-based RL that achieves a new state of the art performance on the challenging Craftax-classic benchmark, an open-world 2D survival game that requires agents to exhibit a wide range of general abilities---such as strong generalization, deep exploration, and long-term re…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors

Joseph Ortiz, Antoine Dedieu, Wolfgang Lehrach, J Swaroop Guntupalli, Carter Wendelken, Ahmad Humayun +4

NeurIPS 2024poster

Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in some respects, agents are often remarkably brittle to minor vi…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗