Gautam Singh

CV · X · LinkedIn · Github · Scholar

Gautam Singh

ML Postdoctoral Research Staff @ Lawrence Livermore National Laboratory (LLNL)

I am interested in developing generative and foundation models, as well as agentic systems, that can infer latent causal structure, learn continually, and adapt with fewer interactions with their environments. I am also interested in scientific applications of agentic AI, including self-driving laboratories for biological discovery, protein design, and biological sequence characterization.

In the past, I have done internships at NVIDIA Research and Amazon, and I spent three years working at IBM Research. I obtained a B.Tech. at IIT Guwahati and a Ph.D. in Computer Science at Rutgers University, advised by Prof. Sungjin Ahn.

 

Lawrence Livermore National Laboratory (LLNL) NVIDIA Research Amazon Science logo Rutgers University logo IBM Research logo KAIST logo IIT Madras logo IIT Guwahati logo

Selected Works

Equal contributions are denoted using {}.

Peer-Reviewed

2026

  • Learning Reasoning World Models for Parallel Code
    • Gautam Singh, Arjun Guha, Bhavya Kailkhura, Harshitha Menon
    • TLDR: Propose Parallel-Code World Models (PCWMs), LLMs that utilize reasoning to model the causal process of arriving at tool/profiler outcomes from parallel source code (e.g., OpenMP code).
    • COLM 2026 [pdf]

2025

  • Can Program Search Help LLMs Write Better Parallel Code?
    • Gautam Singh, Arjun Guha, Bhavya Kailkhura, Harshitha Menon
    • NeurIPS 2025 Workshop (DL4C) 
  • Dreamweaver: Learning Compositional World Representations from Pixels
    • Junyeob Baek, Yi-Fu Wu, Gautam Singh, Sungjin Ahn
    • ICLR 2025 [pdf]

2024

  • Slot State Space Models
    • Jindong Jiang, Fei Deng, Gautam Singh, Minseung Lee, Sungjin Ahn
    • NeurIPS 2024 [pdf] [project]
  • Parallelized Spatiotemporal Binding
    • Gautam Singh, Yue Wang, Jiawei Yang, Boris Ivanovic, {Sungjin Ahn, Marco Pavone}, Tong Che
    • ICML 2024 [pdf] [project]

2023

  • Imagine the Unseen World: A Systematic Visual Imagination Benchmark
    • {Yeongbin Kim, Gautam Singh}, Junyeong Park, Caglar Gulcehre, Sungjin Ahn
    • NeurIPS 2023 
  • Object-Centric Slot Diffusion
    • Jindong Jiang, Fei Deng, Gautam Singh, Sungjin Ahn
    • NeurIPS 2023 (Spotlight) [pdf]
  • Neural Systematic Binder

2022

  • Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos
  • Illiterate DALL-E Learns to Compose
    • Gautam Singh, Fei Deng, Sungjin Ahn
    • ICLR 2022 [pdf] [project] [code]

2021

  • Structured World Belief for Reinforcement Learning in POMDP
    • Gautam Singh, Skand Peri, Junghyun Kim, Hyunseok Kim, Sungjin Ahn
    • ICML 2021 [pdf] [project]

2020

  • Robustifying Sequential Neural Processes
    • Jaesik Yoon, Gautam Singh, Sungjin Ahn
    • ICML 2020 [pdf]
  • SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
    • {Zhixuan Lin, Yi-Fu Wu, Skand Vishwanath Peri}, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, Sungjin Ahn
    • ICLR 2020 [pdf] [project]

2019

  • Sequential Neural Processes
    • {Gautam Singh, Jaesik Yoon}, Sungjin Ahn
    • NeurIPS 2019 (Spotlight) [pdf] [project] [code]

Talks, Posters & Blogs

2026

  • Powering Genome Foundation Model Training with LLNL HPC
    • Gautam Singh, Joseph Wakim, Brian Bartoldson, Bhavya Kailkhura
    • [slides] [poster]

Media Coverage

Service