Publications

Google Scholar

2025

Monte Carlo Tree Diffusion for System 2 Planning

Jaesik Yoon, Hyeonseo Cho, Doojin Baek, Yoshua Bengio, Sungjin Ahn ICML 25 Spotlight (Top 2.5%) [arXiv] [webpage] System 2 Planning Diffusion

Dreamweaver: Learning Compositional World Models from Pixels

Junyeob Baek, Yi-Fu Wu, Gautam Singh, Sungjin Ahn ICLR 25 [arXiv] [webpage] [code] World Model Compositionality

MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory

Junyeong Park*, Junmo Cho*, Sungjin Ahn ICLR 25 [arXiv] [webpage] World Model Embodied AI

Search-Based Correction of Reasoning Chains for Language Models

Minsu Kim, Jean-Pierre Falet, Oliver E. Richardson, Xiaoyin Chen, Moksh Jain, Sungjin Ahn, Sungsoo Ahn, Yoshua Bengio [arXiv] LLM System 2

Adaptive Cyclic Diffusion for Inference Scaling

Gyubin Lee, Truong Nhat Nguyen Bao, Jaesik Yoon, Dongwoo Lee, Minsu Kim, Yoshua Bengio, Sungjin Ahn [arXiv] System 2 Planning Diffusion

Extendable Planning via Multiscale Diffusion

Chang Chen*, Hany Hamed*, Doojin Baek, Taegu Kang, Samyeol Roh, Yoshua Bengio, Sungjin Ahn [arXiv] System 2 Planning Diffusion

2024

Slot State Space Models

Jindong Jiang, Fei Deng, Gautam Singh, Minseung Lee, Sungjin Ahn NeurIPS 24 [arXiv] [webpage] [code] World Model

Neural Language of Thought Models

Yi-Fu Wu, Minseung Lee, Sungjin Ahn ICLR 24 [arXiv] [poster] [code] World Model Visual Abstraction & Reasoning Compositionality

poster

692.8KB

Spatially-Aware Transformers for Embodied Agents

{Junmo Cho*, Jaesik Yoon*}, Sungjin Ahn ICLR 24 Spotlight (Top 5%) [arXiv] [code] Embodied AI World Model

Simple Hierarchical Planning with Diffusion

Chang Chen, Fei Deng, Kenji Kawaguchi, Caglar Gulcehre, Sungjin Ahn

^*

Collaboration with Google DeepMind and NUS ICLR 24 [arXiv] [code] Planning World Model

Learning to Compose: Improving Object Centric Learning by Injecting Compositionality

Whie Jung, Jaehoon Yoo, Sungjin Ahn, Seunghoon Hong ICLR 24 [pdf] Compositionality

PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer

Chang Chen, Junyeob Baek, Fei Deng, Kenji Kawaguchi, Caglar Gulcehre, Sungjin Ahn ICML 24 [arXiv] [code] Planning World Model

Parallelized Spatiotemporal Slot Binding for Videos

Gautam Singh, Yue Wang, Jiawei Yang, Boris Ivanovic, Sungjin Ahn, Marco Pavone, Tong Che

^*

Collaboration with NVIDIA Research ICML 24 [arXiv] Visual Abstraction & Reasoning Compositionality World Model

Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming

{Hany Hamed*, Subin Kim*}, Dongyeong Kim, Jaesik Yoon, Sungjin Ahn ICML 24 [arXiv] [webpage] [code] Planning World Model

2023

Object-Centric Slot Diffusion

Jindong Jiang, Fei Deng, Gautam Singh, Sungjin Ahn NeurIPS 23 Spotlight [arXiv] [webpage] [code]

Representation Generative Model

Facing Off World Model Backbones: RNNs, Transformers, and S4

Fei Deng, Junyeong Park, Sungjin Ahn NeurIPS 23 [arXiv] [webpage]

World Model RL

Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models

Yeongbin Kim*, Gautam Singh*, Junyeong Park, Caglar Gulcehre, Sungjin Ahn

^*

Collaboration with Google DeepMind NeurIPS 23 [arXiv] [webpage] [code & dataset]

Visual Abstraction & Reasoning Compositionality World Model

An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning

Jaesik Yoon, Yi-Fu Wu, Heechul Bae, Sungjin Ahn ICML 23 [arXiv] [webpage] [code]

Representation RL Visual Reasoning

Neural Systematic Binder

Gautam Singh, Yeongbin Kim, Sungjin Ahn ICLR 23 [arXiv] [project] [code]

Representation Visual Reasoning

Object-Centric Semantic Vector Quantization

Yi-Fu Wu, Minseung Lee, Sungjin Ahn NeurIPS 2023 Workshop on Causal Representation Learning [pdf]

Representation Causality

2022

Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos

Gautam Singh, Yi-Fu Wu, Sungjin Ahn NeurIPS 22 [arXiv] [project] [code] [tweet]

Representation World Model

DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations

Fei Deng, Ingook Jang, Sungjin Ahn ICML 22 [pdf] [code]

Representation World Model RL

Illiterate DALLE Learns to Compose

Gautam Singh, Fei Deng, Sungjin Ahn ICLR 22 [pdf] [project] [code]

Representation Generative Model

2021

Structured World Belief for Reinforcement Learning in POMDP

Gautam Signh, Skand Peri, Junghyun Kim, Hyunseok Kim, Sungjin Ahn ICML 21 [pdf] [project]

Representation World Model RL

Generative Video Transformer: Can Objects be the Words?

Yi-Fu Wu, Jaesik Yoon, Sungjin Ahn ICML 21 [pdf]

ocvt

8377.2KB

Representation World Model Generative Model Visual Reasoning

Generative Scene Graph Networks

Fei Deng, Zuo Zhi, Donghun Lee, Sungjin Ahn ICLR 21 [pdf]

Representation Generative Model Visual Reasoning

ROOTS: Object-Centric Representation and Rendering of 3D Scenes

Chang Chen*, Fei Deng*, Sungjin Ahn JMLR 21 [pdf] [project]

Representation 3D Visual Reasoning

DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations

Fei Deng, Ingook Jang, Sungjin Ahn NeurIPS 21 Deep RL Workshop [arXiv]

Representation World Model RL

TransDreamer: Reinforcement Learning with Transformer World Models

Chang Chen, Jaesik Yoon, Yi-Fu Wu, Sungjin Ahn NeurIPS 21 Deep RL Workshop [arXiv] [code]

World Model RL

Learning Representations for Zero-Shot Image Generation without Text

Gautam Singh, Fei Deng, Sungjin Ahn NeurIPS 21 Workshop on Controllable Generative Modeling in Language and Vision [pdf]

Representation Generative Model

2020

Generative Neurosymbolic Machines

J. Jiang and S. Ahn NeurIPS 20 [arxiv] [code] Spotlight (top 4%, 395/9454 submissions)

Representation Generative Model Visual Reasoning

Improving Generative Imagination in Object-Centric World Models

Z. Lin, Y. Wu, S. Peri, B. Fu, J. Jiang, S. Ahn ICML 20 [pdf] [project] [code]

Representation Generative Model World Model Visual Reasoning

Robustifying Sequential Neural Processes

J. Yoon, G. Singh, and S. Ahn ICML 20 [arxiv]

World Model

SCALOR: Generative World Models with Scalable Object Representations

{J. Jiang, S. Janghorbani}, G. Melo, and S. Ahn ICLR 20 [arxiv] [project] [code]

Representation Generative Model World Model

SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition

{Z. Lin, Y. Wu, S. Peri}, W. Sun, G. Singh, F. Deng, J. Jiang, S. Ahn ICLR 20 [pdf] [project] [code]

Representation

Hierarchical Decomposition and Generation of Scenes with Compositional Objects

F. Deng, Z. Zhi, S. Ahn ICML 20 Workshop on Object-Oriented Learning [pdf] Spotlight

Representation Generative Model

Generating Stochastic Object Dynamics in Scenes

Z. Lin, Y. Wu, S. Peri, B. Fu, J. Jiang, and S. Ahn ICML 20 Workshop on Object-Oriented Learning [pdf]

Representation Generative Model World Model

2019

Sequential Neural Processes

{Gautam Singh, Jaesik Yoon}, Youngsung Son, Sungjin Ahn NeurIPS 19 [paper] [project] [code] Spotlight(top 2.4% = 163/6743)

World Model

Variational Temporal Abstraction

Taesup Kim, {Sungjin Ahn, Yoshua Bengio} NeurIPS 19

Temporal Abstraction Skill World Model

Neural Multisensory Scene Inference

Jae Hyun Lim, Pedro O. Pinheiro, Negar Rostamzadeh, Christopher Pal, Sungjin Ahn NeurIPS 19

Representation

Domain-Adaptive Single-View 3D Reconstruction

Pedro O. Pinheiro, Negar Rostamzadeh, Sungjin Ahn ICCV 19 Oral Presentation (top 4.3%)

Generative Model 3D

Generative Hierarchical Models for Parts, Objects, and Scenes

Fei Deng, Zhou Zhi, Sungjin Ahn arXiv 19

Representation Generative Model

Reinforced Imitation in Heterogeneous Action Space

Konrad Zolna, Negar Rostamzadeh, Yoshua Bengio, {Sungjin Ahn, Pedro O. Pinheiro} arXiv 19

2018

Bayesian Model-Agnostic Meta-Learning

{Jaesik Yoon, Taesup Kim}, Ousmane Dia, Sungwoong Kim, Yoshua Bengio, Sungjin Ahn NeurIPS 18 Spotlight (top 3.5% = 168/4856)

Meta-Learning Bayesian

Reinforced Imitation Learning from Observation

Konrad Zolna, Negar Rostamzadeh, Yoshua Bengio, {Sungjin Ahn, Pedro O. Pinheiro} NeurIPS 18 Workshop on Imitation Learning and Its Challenges in Robotics

2017

Hierarchical Multiscale Recurrent Neural Networks

Junyoung Chung, Sungjin Ahn, Yoshua Bengio ICLR 17

Denoising Criterion for Variational Auto-Encoding Framework

Daniel Jiwoong Im, Sungjin Ahn, Roland Memisevic, Yoshua Bengio AAAI 17

SENA: Preserving Social Structure for Network Embedding

Sanghyun Hong, Tanmoy Chakraborty, Sungjin Ahn, Ghaith Husari, Noseong Park ACM Hypertext and Social Media 17

2016

Pointing the Unknown Words Oral Presentation

Caglar Glucehre, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou, Yoshua Bengio ACL 16, Oral Presentation

Generating Factoid Questions

{Iulian Vlad Serban, Alberto García-Durán}, Caglar Gulcehre, Sungjin Ahn, Sarath Chandar, Aaron Courville, Yoshua Bengio ACL 16

Scalable MCMC for Mixed Membership Stochastic Blockmodels

{Wenzhe Li, Sungjin Ahn}, Max Welling AISTATS 16

Scalable Overlapping Community Detection Best Paper Award

Ismail El-Helw, Rutger Hofman, Wenzhe Li, Sungjin Ahn, Max Welling, Henri Bal ParLearning 16, Best Paper Award

Learning Latent Multiscale Structure using Recurrent Neural Networks

Junyoung Chung, Sungjin Ahn, Yoshua Bengio NIPS 16 Workshop on Neural Abstract Machines & Program Induction (NAMPI)

A Neural Knowledge Language Model

Sungjin Ahn, Heeyoul Choi, Tanel Parnamaa, Yoshua Bengio arXiv 16

Hierarchical Memory Networks

Sarath Chandar, Sungjin Ahn, Hugo Larochelle, Pascal Vincent, Gerald Tesauro, Yoshua Bengio arXiv 16

~ 2015 (Selected Publications)

Stochastic Gradient MCMC: Algorithms and Applications

Ph.D. Dissertation

Large-Scale Distributed Bayesian Matrix Factorization using Stochastic Gradient MCMC

Sungjin Ahn, Anoop Korattikara, Nathan Liu, Suju Rajan, Max Welling KDD 15

Distributed Stochastic Gradient MCMC

Sungjin Ahn, Babak Shahbaba, Max Welling ICML 14

Distributed and Adaptive Darting Monte Carlo through Regenerations

Sungjin Ahn, Yutian Chen, Max Welling AISTATS 13

Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring Best Paper Award

Sungjin Ahn, Anoop Korattikara, Max Welling ICML 12, Best Paper Award