Gautam Singh

CV · Twitter · LinkedIn · Github · Scholar

I am an ML Postdoctoral Researcher @ Lawrence Livermore National Laboratory.

I am interested in generative models that are capable of human-like robust out-of-distribution generalization with respect to the data they have seen. Toward this, I seek to develop representations and learning algorithms that can support system-2 reasoning and improve learning efficency. I am also interested in applying machine learning to address difficult challenges that can make a positive long-term impact on humanity.

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

 

---

Recent News

• May 2024: Our work, Parallelized Spatiotemporal Binding, has now been accepted at ICML 2024!
• Feb 2024: Our new work, Parallelized Spatiotemporal Binding, is now on arXiv!
• Sep 2023: Joined as a research intern at NVIDIA Research collaborating with Gerry Che and Yue Wang.
• May 2023: Gave a talk at the University of Toronto AI in Robotics (AIR) seminar, focusing on representation learning for systematic generalization. YouTube link here!
• Feb 2023: We have released the code and datasets for our ICLR'23 paper Neural Systematic Binder here!

---

Selected Publications

Equal contributions are denoted using {}.

2025

• 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
  
  • Gautam Singh, Yeongbin Kim, Sungjin Ahn
  • ICLR 2023 [pdf] [project] [code] [data]

2022

• Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos
  
  • Gautam Singh, Yi-Fu Wu, Sungjin Ahn
  • NeurIPS 2022 [pdf] [poster] [project] [code] [data]

• 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]

---

Media

• Oct 2021: Rutgers University’s AI Researchers Propose A Slot-Based Autoencoder Architecture, Called SLot Attention TransformEr (SLATE)

---

Service

• Conference Reviewer: ICML24, NeurIPS23, ICLR23, NeurIPS22, ICML22
• Workshop Reviewer: OSC@ICLR22