Honglak Lee

Professor of CSE
U. Michigan, Ann Arbor
&
Executive VP and Chief Scientist
LG AI Research

Sloan Research Fellow

---

Address (UM):
3773 Bob and Betty Beyster Building
2260 Hayward Street
Ann Arbor, MI 48109

Email:

---

Main

Biography

News

Professional Service

Research

Research Group

Publications

Teaching

Prospective Students

Publications

2022

Seohong Park, Jongwook Choi, Jaekyeom Kim, Honglak Lee, Gunhee Kim.
Lipschitz-constrained Unsupervised Skill Discovery.
In ICLR, 2022. [Arxiv]

Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee.
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning.
In ICLR, 2022. [Arxiv]

Taehoon Kim, Gwangmo Song, Sihaeng Lee, Sangyun Kim, Yewon Seo, Soonyoung Lee, Seung Hwan Kim, Honglak Lee, Kyunghoon Bae.
L-Verse: Bidirectional Generation Between Image and Text.
In CVPR, 2022. [Arxiv]
Oral presentation

Yijie Guo, Qiucheng Wu, Honglak Lee.
Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks.
In AAAI, 2022.

Anthony Z. Liu, Sungryull Sohn, Mahdi Qazwini, Honglak Lee.
Learning Parameterized Task Structure for Generalization to Unseen Entities.
In AAAI, 2022. [Arxiv]

2021

Christopher Hoang, Sungryull Sohn, Jongwook Choi, Wilka Carvalho, Honglak Lee.
Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning.
In NeurIPS, 2021. [Arxiv]

Izzeddin Gur, Natasha Jaques, Yingjie Miao, Jongwook Choi, Manoj Tiwari, Honglak Lee, Aleksandra Faust.
Environment Generation for Zero-Shot Compositional Reinforcement Learning.
In NeurIPS, 2021. [Arxiv]

Hankook Lee, Kibok Lee, Kimin Lee, Honglak Lee, Jinwoo Shin.
Improving Transferability of Representations via Augmentation-Aware Self-Supervision.
In NeurIPS, 2021. [Arxiv]

Simon Kornblith, Ting Chen, Honglak Lee, Mohammad Norouzi.
Why Do Better Loss Functions Lead to Less Transferable Features?
In NeurIPS, 2021. [Arxiv]

Wilka Carvalho, Anthony Liang, Kimin Lee, Sungryull Sohn, Honglak Lee, Richard L. Lewis, Satinder Singh.
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment.
In IJCAI, 2021. [Arxiv]

Younggyo Seo, Lili Chen, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee.
State Entropy Maximization with Random Encoders for Efficient Exploration.
In ICML, 2021. [Arxiv]

Jongwook Choi, Archit Sharma, Honglak Lee, Sergey Levine, Shixiang Shane Gu.
Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning.
In ICML, 2021. [Arxiv]

Sungryull Sohn, Sungtae Lee, Jongwook Choi, Harm van Seijen, Mehdi Fatemi, Honglak Lee.
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks.
In ICML, 2021. [Arxiv]

Yunke Wang, Chang Xu, Bo Du, Honglak Lee.
Learning to Weight Imperfect Demonstrations.
In ICML, 2021.

Jing Yu Koh, Honglak Lee, Yinfei Yang, Jason Baldridge, Peter Anderson.
Pathdreamer: A World Model for Indoor Navigation.
In ICCV, 2021. [Arxiv]

Han Zhang, Jing Yu Koh, Jason Baldridge, Honglak Lee, Yinfei Yang.
Cross-Modal Contrastive Learning for Text-to-Image Generation.
In CVPR, 2021. [Arxiv]

Tianhao Zhang, Hung-Yu Tseng, Lu Jiang, Weilong Yang, Honglak Lee, Irfan Essa.
Text as Neural Operator: Image Manipulation by Text Instruction.
In ACM Multimedia, 2021. [Arxiv]

Wonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas Huang, Hyungsuk Yoon, Honglak Lee, Seunghoon Hong.
Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction.
In ICLR, 2021.

John D. Co-Reyes, Yingjie Miao, Daiyi Peng, Esteban Real, Sergey Levine, Quoc V. Le, Honglak Lee, Aleksandra Faust.
Evolving Reinforcement Learning Algorithms.
In ICLR, 2021. [Arxiv]
Oral presentation

Yijie Guo, Shengyu Feng, Nicolas Le Roux, Ed Chi, Honglak Lee, Minmin Chen.
Batch Reinforcement Learning Through Continuation Method.
In ICLR, 2021.

Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, Honglak Lee.
i-Mix: A Strategy for Regularizing Contrastive Representation Learning.
In ICLR, 2021. [Arxiv]

Zhengli Zhao, Sameer Singh, Honglak Lee, Zizhao Zhang, Augustus Odena, Han Zhang.
Improved Consistency Regularization for GANs.
In AAAI, 2021. [Arxiv]

Jing Yu Koh, Jason Baldridge, Honglak Lee, Yinfei Yang.
Text-to-Image Generation Grounded by Fine-Grained User Attention.
In WACV, 2021. [Arxiv]

2020

Yijie Guo, Jongwook Choi, Marcin Moczulski, Shengyu Feng, Samy Bengio, Mohammad Norouzi, Honglak Lee.
Memory-based Trajectory-conditioned Policy for Long-Horizon, Sparse-Reward Tasks.
In NeurIPS, 2020. [Arxiv]

Kuang-Huei Lee, Ian Fischer, Anthony Liu, Yijie Guo, Honglak Lee, John Canny, Sergio Guadarrama.
Predictive Information Accelerates Learning in RL.
In NeurIPS, 2020. [Arxiv]

Guangxiang Zhu, Minghao Zhang, Honglak Lee, Chongjie Zhang.
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning.
In NeurIPS, 2020. [Arxiv]

Krzysztof Choromanski, Jared Quincy Davis, Valerii Likhosherstov, Xingyou Song, Jean-Jacques Slotine, Jacob Varley, Honglak Lee, Adrian Weller, Vikas Sindhwani.
An Ode to an ODE.
In NeurIPS, 2020. [Arxiv]

Lajanugen Logeswaran, Ann Lee, Myle Ott, Honglak Lee, Marc'Aurelio Ranzato, Arthur Szlam.
Few-shot Sequence Learning with Transformers.
In NeurIPS Workshop on Meta-Learning, 2020. [Arxiv]

Wonkwang Lee, Donggyun Kim, Seunghoon Hong, Honglak Lee.
High-Fidelity Synthesis with Disentangled Representation.
In ECCV, 2020. [Arxiv]

Haonan Qiu, Chaowei Xiao, Lei Yang, Xinchen Yan, Honglak Lee, Bo Li.
SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing.
In ECCV, 2020. [Arxiv]

Sungryull Sohn, Yinlam Chow, Jayden Ooi, Ofir Nachum, Honglak Lee, Ed Chi, Craig Boutilier.
BRPO: Batch Residual Policy Optimization.
In IJCAI, 2020. [Arxiv]

Kimin Lee, Younggyo Seo, Seunghyun Lee, Honglak Lee, Jinwoo Shin.
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning.
In ICML, 2020. [Arxiv]

Sungryull Sohn, Hyunjae Woo, Jongwook Choi, Honglak Lee.
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
In ICLR, 2020. [Arxiv]

Kimin Lee, Kibok Lee, Jinwoo Shin, Honglak Lee.
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
In ICLR, 2020. [Arxiv]

Han Zhang, Zizhao Zhang, Augustus Odena, Honglak Lee.
Consistency Regularization for Generative Adversarial Networks
In ICLR, 2020. [Arxiv]

Jared Quincy Davis, Krzysztof Choromanski, Jake Varley, Honglak Lee, Jean-Jacques Slotine, Valerii Likhosterov, Adrian Weller, Ameesh Makadia, Vikas Sindhwani.
Time Dependence in Non-Autonomous Neural ODEs.
In ICLR Workshop on Integration of Deep Neural Models and Differential Equations, 2020. [Arxiv]

Janarthanan Rajendran, Richard Lewis, Vivek Veeriah, Honglak Lee, Satinder Singh.
How Should an Agent Practice?
In AAAI, 2020. [Arxiv]

Zizhao Zhang, Han Zhang, Sercan O. Arik, Honglak Lee, Tomas Pfister.
Distilling Effective Supervision From Severe Label Noise.
In CVPR, 2020. [Arxiv]

Haizhong Zheng, Ziqi Zhang, Juncheng Gu, Honglak Lee, Atul Prakash.
Efficient Adversarial Training With Transferable Adversarial Examples.
In CVPR, 2020. [Arxiv]

Suraj Kiran Raman, Aditya Ramesh, Vijayakrishna Naganoor, Shubham Dash, Giridharan Kumaravelu, Honglak Lee.
CompressNet: Generative Compression at Extremely Low Bitrates.
In WACV, 2020. [Arxiv]

2019

Ruben Villegas, Arkanath Pathak, Harini Kannan, Dumitru Erhan, Quoc V. Le, Honglak Lee.
High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks.
In NeurIPS, 2019. [Arxiv]

Matthias Minderer, Chen Sun, Ruben Villegas, Forrester Cole, Kevin Murphy, Honglak Lee.
Unsupervised learning of object structure and dynamics from videos.
In NeurIPS, 2019. [Arxiv]

Ofir Nachum, Haoran Tang, Xingyu Lu, Shixiang Gu, Honglak Lee, Sergey Levine.
Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?
In NeurIPS Workshop on Deep Reinforcement Learning, 2019. [Arxiv]
Oral Presentation

Kibok Lee, Kimin Lee, Jinwoo Shin, Honglak Lee.
Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild.
In ICCV, 2019. [Arxiv]

Yunseok Jang, Tianchen Zhao, Seunghoon Hong, Honglak Lee.
Adversarial Defense via Learning to Generate Diverse Attacks.
In ICCV, 2019. [paper]

Seunghoon Hong, Dingdong Yang, Jongwook Choi, Honglak Lee.
Interpretable Text-to-Image Synthesis with Hierarchical Semantic Layout Generation.
In Book chapter of "Explainable AI: Interpreting, Explaining and Visualizing Deep Learning", 2019. [paper]

Lajanugen Logeswaran, Ming-Wei Chang, Kristina Toutanova, Kenton Lee, Jacob Devlin, Honglak Lee.
Zero-Shot Entity Linking by Reading Entity Descriptions.
In ACL, 2019. [paper]
Finalist for the Best Paper Award

Woojoo Sim*, Kibok Lee*, Dingdong Yang, Jaeseung Jeong, Ji-Suk Hong,Sooryong Lee, and Honglak Lee.
Automatic correction of lithography hotspots with a deep generative model.
In SPIE Advanced Lithography Symposium, 2019. [paper]
Oral presentation

Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li, Jinwoo Shin.
Robust Inference via Generative Classifiers for Handling Noisy Labels.
In ICML, 2019. [Arxiv]

Simon Kornblith, Mohammad Norouzi, Honglak Lee, Geoffrey Hinton.
Similarity of Neural Network Representations Revisited.
In ICML, 2019. [Arxiv]
(Best Research Paper Award at the ICLR 2019 Workshop on Debugging Machine Learning Models.)

Danijar Hafner, Timothy Lillicrap, Ian Fischer, Ruben Villegas, David Ha, Honglak Lee, James Davidson.
Learning Latent Dynamics for Planning from Pixels.
In ICML, 2019. [Arxiv]

Dingdong Yang, Seunghoon Hong, Yunseok Jang, Tianchen Zhao, Honglak Lee.
Diversity-Sensitive Conditional Generative Adversarial Networks.
In ICLR, 2019. [Arxiv]

Jongwook Choi, Yijie Guo, Marcin Moczulski, Junhyuk Oh, Neal Wu, Mohammad Norouzi, Honglak Lee.
Contingency-Aware Exploration in Reinforcement Learning.
In ICLR, 2019. [Arxiv]
(Oral presentation at NeurIPS 2018 Workshop on Deep Reinforcement Learning; top ~10 out of ~130 accepted papers)

Ofir Nachum, Shixiang Gu, Honglak Lee, Sergey Levine.
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning.
In ICLR, 2019. [Arxiv]
(Oral presentation at NeurIPS 2018 Workshop on Deep Reinforcement Learning; top ~10 out of ~130 accepted papers)

2018

Sungryull Sohn, Junhyuk Oh, Honglak Lee.
Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies.
In NeurIPS, 2018. [Arxiv]
(Oral presentation at ICML 2018 Workshop on Lifelong Learning: A Reinforcement Learning Approach)

Jacob Buckman, Danijar Hafner, George Tucker, Eugene Brevdo, Honglak Lee.
Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion.
In NeurIPS, 2018. [Arxiv]
Oral presentation

Ofir Nachum, Shixiang Gu, Honglak Lee, Sergey Levine.
Data-Efficient Hierarchical Reinforcement Learning.
In NeurIPS, 2018. [Arxiv]

Kimin Lee, Kibok Lee, Honglak Lee, Jinwoo Shin.
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks.
In NeurIPS, 2018. [Arxiv]
Spotlight

Seunghoon Hong, Xinchen Yan, Thomas Huang, Honglak Lee.
Learning Hierarchical Semantic Image Manipulation through Structured Representations.
In NeurIPS, 2018. [Arxiv]

Lajanugen Logeswaran, Honglak Lee, Samy Bengio.
Content preserving text generation with attribute controls.
In NeurIPS, 2018. [pdf coming soon]

Yijie Guo, Junhyuk Oh, Satinder Singh, Honglak Lee.
Generative Adversarial Self-Imitation Learning.
In NeurIPS Workshop on Deep Reinforcement Learning, 2018. [Arxiv]

Xinchen Yan, Akash Rastogi, Ruben Villegas, Kalyan Sunkavalli, Eli Shechtman, Sunil Hadap, Ersin Yumer, Honglak Lee.
MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics.
In ECCV, 2018. [Arxiv]

Nevan Wichers, Ruben Villegas, Dumitru Erhan, Honglak Lee.
Hierarchical Long-term Video Prediction without Supervision.
In ICML, 2018. [pdf] [arXiv] [project website] [code]

Junhyuk Oh*, Yijie Guo*, Satinder Singh, Honglak Lee.
Self-Imitation Learning.
In ICML, 2018. [pdf] [supplementary material]

Yuting Zhang, Yijie Guo, Yixin Jin, Yijun Luo, Zhiyuan He, Honglak Lee.
Unsupervised Discovery of Object Landmarks as Structural Representations.
In CVPR, 2018. [arXiv]
Oral presentation

Ruben Villegas, Jimei Yang, Duygu Ceylan, Honglak Lee.
Neural Kinematic Networks for Unsupervised Motion Retargetting.
In CVPR, 2018. [arXiv] [video] [project website]
Oral presentation

Seunghoon Hong, Dingdong Yang, Jongwook Choi, Honglak Lee.
Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis.
In CVPR, 2018. [arXiv]

Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin and Honglak Lee.
Hierarchical Novelty Detection for Visual Object Recognition.
In CVPR, 2018. [arXiv]

Kimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin.
Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples.
In ICLR, 2018 [arXiv]

Lajanugen Logeswaran, Honglak Lee.
An efficient framework for learning sentence representations .
In ICLR, 2018 [arXiv]

Lajanugen Logeswaran, Honglak Lee, Dragomir Radev.
Sentence Ordering and Coherence Modeling using Recurrent Neural Networks.
In AAAI, 2018 [arXiv]

Rui Zhang, Honglak Lee, Lazaros Polymenakos, Dragomir Radev.
Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs.
In AAAI, 2018 [arXiv]

Xinchen Yan, Jasmine Hsu, Mohi Khansari, Yunfei Bai, Arkanath Pathak, Abhinav Gupta, James Davidson, Honglak Lee.
Learning 6-DOF Grasping Interaction with Deep Geometry-aware 3D Representations.
In ICRA, 2018 [arXiv]

2017

Junhyuk Oh, Satinder Singh, Honglak Lee.
Value Prediction Network.
In NIPS, 2017 [pdf] [arXiv (full version)] [code]

Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin, Jonathon Shlens.
Exploring the structure of a real-time, arbitrary neural artistic stylization network.
In BMVC, 2017 [pdf] [arXiv (full version)] [code]
Oral presentation

Ruben Villegas, Jimei Yang, Xunyu Lin, Yuliang Zou, Sungryull Sohn, Honglak Lee.
Learning to Generate Long-term Future via Hierarchical Prediction.
In ICML, 2017 [pdf] [supplemenatary material] [arXiv (full version)] [project website with code and video]

Junhyuk Oh, Satinder Singh, Honglak Lee, Pushmeet Kohli.
Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning.
In ICML, 2017 [pdf] [supplementary material] [arXiv (full version)] [project website with code and video]

Yuting Zhang, Luyao Yuan, Yijie Guo, Zhiyuan He, I-An Huang, Honglak Lee.
Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queries.
In CVPR, 2017 [pdf] [arXiv (full version)] [project website with code]
Spotlight

Seunghoon Hong, Donghun Yeo, Suha Kwak, Honglak Lee, Bohyung Han.
Weakly Supervised Semantic Segmentation using Web-Crawled Videos.
In CVPR, 2017 [pdf] [arXiv (full version)]
Spotlight

Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee.
Decomposing Motion and Content for Natural Video Sequence Prediction.
In ICLR, 2017 [pdf] [arXiv] [project website with code and video]

Anna Gilbert, Yi Zhang, Kibok Lee, Yuting Zhang, Honglak Lee.
Towards Understanding the Invertibility of Convolutional Neural Networks.
In IJCAI, 2017 [pdf (arXiv, full version)]

Weiran Wang, Xinchen Yan, Honglak Lee, Karen Livescu.
Deep Variational Canonical Correlation Analysis.
Technical Report [arXiv]

2016

Scott Reed, Zeynep Akata, Santosh Mohan, Samuel Tenka, Bernt Schiele, Honglak Lee.
Learning What and Where to Draw.
In NIPS, 2016 [pdf] [arXiv (full version)] [code]
Oral presentation

Xinchen Yan, Jimei Yang, Ersin Yumer, Yijie Guo, Honglak Lee .
Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision.
In NIPS, 2016 [pdf] [arXiv (full version)] [code]

Xinchen Yan, Jimei Yang, Kihyuk Sohn, Honglak Lee.
Attribute2Image: Conditional Image Generation from Visual Attributes.
In ECCV, 2016 [pdf] [arXiv preprint] [code]

Yuting Zhang, Kibok Lee, and Honglak Lee.
Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification.
In ICML, 2016 [pdf] [supplementary material] [arXiv] [code]

Wenling Shang, Kihyuk Sohn, Diogo Almeida, and Honglak Lee .
Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units.
In ICML, 2016 [pdf] [full version with appendix] [arXiv preprint]

Junhyuk Oh, Valliappa Chockalingam, Satinder Singh, and Honglak Lee.
Control of Memory, Active Perception, and Action in Minecraft.
In ICML, 2016 [pdf] [arXiv (full version with appendix)] [project website with code and video]

Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, and Honglak Lee.
Generative Adversarial Text to Image Synthesis.
In ICML, 2016 [pdf] [arXiv] [code]

Seunghoon Hong, Junhyuk Oh, Bohyung Han, Honglak Lee.
Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network.
In CVPR, 2016 [pdf] [arXiv (full version with appendix)] [project website with code]
Spotlight

Jimei Yang, Brian Price, Scott Cohen, Ming-Hsuan Yang, Honglak Lee.
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network.
In CVPR, 2016 [pdf] [arXiv (full version with appendix)] [code]
Spotlight

Scott Reed, Zeynep Akata, Honglak Lee, Bernt Schiele.
Learning Deep Representations of Fine-Grained Visual Descriptions.
In CVPR, 2016 [pdf] [arXiv] [code and data]
Spotlight

Xiaoxiao Guo, Satinder Singh, Richard Lewis, Honglak Lee.
Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games.
In IJCAI, 2016 [pdf] [arXiv]

Wenling Shang, Kihyuk Sohn, Honglak Lee, Anna Gilbert.
Discriminative Training of Structured Dictionaries via Block Orthogonal Matching Pursuit.
In SIAM International Conference on Data Mining (SDM), 2016 [pdf]

Rui Zhang, Dragomir Radev, Honglak Lee.
Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents.
In the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 2016 [pdf] [arXiv]

2015

Scott Reed, Yi Zhang, Yuting Zhang, Honglak Lee.
Deep Visual Analogy-Making.
In Advances in Neural Information Processing Systems (NIPS), 2015. [pdf] [supplementary material] .
Oral presentation

Junhyuk Oh, Xiaoxiao Guo, Honglak Lee, Satinder Singh, Richard Lewis.
Action-Conditional Video Prediction using Deep Networks in Atari Games.
In Advances in Neural Information Processing Systems (NIPS), 2015. [pdf] [supplementary material] [arXiv] [project website with code and videos] .
Spotlight

Kihyuk Sohn, Xinchen Yan, Honglak Lee.
Learning Structured Output Representation using Deep Conditional Generative Models.
In Advances in Neural Information Processing Systems (NIPS), 2015. [pdf] [supplementary material] .

Jimei Yang, Scott Reed, Ming-Hsuan Yang, Honglak Lee.
Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis.
In Advances in Neural Information Processing Systems (NIPS), 2015. [pdf] [code] [video] .

Yuting Zhang, Kihyuk Sohn, Ruben Villegas, Gang Pan, and Honglak Lee.
Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [pdf] [bib] [supplementary material] [full version with appendix] [code] Oral presentation .
OpenCV People’s Vote Winning Paper (1st Place).

Zeynep Akata, Scott Reed, Daniel Walter, Honglak Lee, and Bernt Schiele.
Evaluation of Output Embeddings for Fine-Grained Image Classification.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [pdf] [bib] [code]

Scott Reed, Honglak Lee, Dragomir Anguelov, Christian Szegedy, Dumitru Erhan, Andrew Rabinovich.
Training Deep Neural Networks on Noisy Labels with Bootstrapping.
In the Workshop at the International Conference on Learning Representation (ICLR), 2015. [pdf] [bib] .

Changhan Wang, Xinchen Yan, Max Smith, Kanika Kochhar, Marcie Rubin, Stephen M. Warren, James Wrobel, and Honglak Lee.
A Unified Framework for Automatic Wound Segmentation and Analysis with Deep Convolutional Neural Networks.
To appear at the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015. [pdf] .

Ian Lenz, Honglak Lee, Ashutosh Saxena.
Deep Learning for Detecting Robotic Grasps.
To appear in International Journal on Robotics Research (IJRR), vol. 34, no. 4-5, pp. 705--724, 2015. [pdf] [bib] [project] [code]
(An earlier version was presented in Robotics Science and Systems (RSS) 2013.).

2014

Kihyuk Sohn, Wenling Shang, and Honglak Lee.
Improved Multimodal Deep Learning with Variation of Information.
In Advances in Neural Information Processing Systems (NIPS) 27, 2014. [pdf] [bib] [full version with appendix] .

Xiaoxiao Guo, Satinder Singh, Honglak Lee, Richard Lewis, Xiaoshi Wang.
Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning.
In Advances in Neural Information Processing Systems (NIPS) 27, 2014. [pdf] [bib] .

Scott Reed, Kihyuk Sohn, Yuting Zhang, Honglak Lee.
Learning to Disentangle Factors of Variation with Manifold Interaction.
In Proceedings of the 31st International Conference on Machine Learning (ICML), 2014. [pdf] [bib] [code]
(A previous version was presented at the NIPS Workshop on Deep Learning, 2013.)

Roni Mittelman, Benjamin Kuipers, Silvio Savarese, Honglak Lee.
Structured Recurrent Temporal Restricted Boltzmann Machines.
In Proceedings of the 31st International Conference on Machine Learning (ICML), 2014. [pdf] [bib] [supplementary material] [code]
(A previous version was presented at the NIPS Workshop on Deep Learning, 2013.)

Alex Burnap, Yi Ren, Honglak Lee, Richard Gonzalez, Panos Y Papalambros.
Improving Preference Prediction Accuracy with Feature Learning.
In Proceedings of the ASME International Design Engineering Technical Conferences (IDETC), 2014. [pdf] [bib]

2013

Forest Agostinelli, Michael Anderson, Honglak Lee.
Adaptive Multi-Column Deep Neural Networks with Application to Robust Image Denoising.
In Advances in Neural Information Processing Systems (NIPS) 26, 2013. [pdf] [bib] [project/code] .

Kihyuk Sohn, Guanyu Zhou, Chansoo Lee, and Honglak Lee.
Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines.
In Proceedings of the 30th International Conference on Machine Learning (ICML), 2013. [pdf] [bib] [supplementary material] [full version with appendix] [project/code]
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2012.) .

Andrew Kae*, Kihyuk Sohn*, Honglak Lee, and Erik Learned-Miller.
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013. [pdf] [bib] [project/code]
* indicates equal contributions.

Roni Mittelman, Honglak Lee, Benjamin Kuipers, and Silvio Savarese.
Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013. [pdf] [bib] [code]

Ian Lenz, Honglak Lee, Ashutosh Saxena.
Deep Learning for Detecting Robotic Grasps.
In Robotics: Science and Systems (RSS), 2013. [pdf] [bib] [project] [code]
(A previous version appeared at the International Conference on Learning Representations (ICLR), 2013.) .

Yelin Kim, Honglak Lee, and Emily Mower Provost.
Deep Learning for Robust Feature Generation in Audio-Visual Emotion Recognition.
In International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2013. [pdf] [bib]

2012

Gary Huang, Marwan Mattar, Honglak Lee, Erik Learned-Miller.
Learning to Align from Scratch.
In Advances in Neural Information Processing Systems (NIPS) 25, 2012. [pdf] [bib]

Kihyuk Sohn and Honglak Lee.
Learning Invariant Representations with Local Transformations.
In Proceedings of the 29th International Conference on Machine Learning (ICML), 2012. [pdf] [bib]

Gary Huang, Honglak Lee, and Erik Learned-Miller.
Learning Hierarchical Representations for Face Verification with Convolutional Deep Belief Networks.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. [pdf] [bib]

Min Sun, Murali Telaprolu, Honglak Lee, and Silvio Savarese.
An Efficient Branch-and-Bound Algorithm for Optimal Human Pose Estimation.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. [pdf] [bib] [supplementary material] [code]

Guanyu Zhou, Kihyuk Sohn, and Honglak Lee.
Online Incremental Feature Learning with Denoising Autoencoders.
In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 22, 2012.
[pdf] [bib] [supplementary material] [full version with appendix]
Oral presentation
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.).

Caoxie Zhang, Honglak Lee, and Kang G. Shin.
Efficient Distributed Linear Classification Algorithms via the Alternating Direction Method of Multipliers.
In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 22, 2012. [pdf] [bib] [code]

Min Sun, Murali Telaprolu, Honglak Lee, and Silvio Savarese.
Efficient and Exact MAP-MRF Inference using Branch and Bound.
In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 22, 2012. [pdf] [bib] [supplementary material] [code]

2011

Kihyuk Sohn, Dae Yon Jung, Honglak Lee, and Alfred Hero III.
Efficient Learning of Sparse, Distributed, Convolutional Feature Representations for Object Recognition.
In Proceedings of 13th International Conference on Computer Vision (ICCV), 2011. [pdf] [bib]

Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng.
Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks.
Communications of the ACM, vol. 54, no. 10, pp. 95-103, 2011. [pdf] [bib] [fulltext] [technical perspective by Geoffrey Hinton] [code] .
Research Highlights.

Juhan Nam, Jiquan Ngiam, Honglak Lee, and Malcolm Slaney.
A classification-based polyphonic piano transcription approach using learned feature representations.
In Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR), 2011. [pdf] [bib]

Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee and Andrew Y. Ng.
Multimodal Deep Learning.
In Proceedings of the 29th International Conference on Machine Learning (ICML), 2011. [pdf] [bib]
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2010. [pdf])

Adam Coates, Honglak Lee and Andrew Y. Ng.
An Analysis of Single-Layer Networks in Unsupervised Feature Learning.
In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 15, 2011. [pdf] [bib] [code] [STL-10 dataset]
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2010. [pdf])

2010 and before

Honglak Lee.
Unsupervised Feature Learning Via Sparse Hierarchical Representations.
Ph.D. Dissertation, Stanford University, Computer Science Department, August 2010. [pdf] [bib]

Aditya Khosla, Yu Cao, Cliff Chiung-Yu Lin, Hsu-Kuang Chiu, Junling Hu, and Honglak Lee.
An integrated machine learning approach to stroke prediction.
Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2010. [pdf] [bib] [code]

Honglak Lee, Yan Largman, Peter Pham, and Andrew Y. Ng.
Unsupervised feature learning for audio classification using convolutional deep belief networks.
Advances in Neural Information Processing Systems (NIPS) 22, 2009.
[pdf] [bib] [code]

Ian J. Goodfellow, Quoc V. Le, Andrew M. Saxe, Honglak Lee, and Andrew Y. Ng.
Measuring invariances in deep networks.
Advances in Neural Information Processing Systems (NIPS) 22, 2009. [pdf] [bib]

Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng.
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations.
In Proceedings of the 26th International Conference on Machine Learning (ICML), 2009. [pdf] [bib] [talk video] [code]
Best Paper Award: Best Application Paper.

Honglak Lee, Rajat Raina, Alex Teichman, and Andrew Y. Ng.
Exponential Family Sparse Coding with Application to Self-taught Learning.
In Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI), 2009. [pdf] [bib]
(A previous version appeared at ICML Workshop on Prior Knowledge for Text and Language, 2008.)

Honglak Lee, Chaitu Ekanadham, and Andrew Y. Ng.
Sparse deep belief net model for visual area V2.
Advances in Neural Information Processing Systems (NIPS) 20, 2008. [pdf] [bib]

Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer, and Andrew Y. Ng.
Self-taught learning: Transfer learning from unlabeled data.
In Proceedings of the 24th International Conference on Machine Learning (ICML), 2007. [pdf] [bib]

Honglak Lee, Alexis Battle, Rajat Raina, and Andrew Y. Ng.
Efficient sparse coding algorithms.
Advances in Neural Information Processing Systems (NIPS) 19, 2007. [pdf] [bib] [code]

Patrick T. McGrath, Honglak Lee, Li Zhang, Antonio A. Iniesta, Alison K. Hottes, Meng How Tan, Nathan J. Hillson, Ping Hu, Lucy Shapiro, and Harley H. McAdams.
High-throughput identification of transcription start sites, conserved promoter motifs, and predicted regulons.
Nature Biotechnology, 25, pp. 584-592 (2007). [pdf] [bib] [fulltext] [pubmed]

Su-In Lee, Honglak Lee, Pieter Abbeel, and Andrew Y. Ng.
Efficient L1 regularized logistic regression.
In Proceedings of the 21st National Conference on Artificial Intelligence (AAAI), 2006. [pdf] [bib] [code]

Honglak Lee, Yirong Shen, Chih-Han Yu, Gurjeet Singh, and Andrew Y. Ng.
Quadruped robot obstacle negotiation via reinforcement learning.
In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2006. [pdf] [bib] [videos]

Erick Delage, Honglak Lee, and Andrew Y. Ng.
A dynamic Bayesian network model for autonomous 3d reconstruction from a single indoor image.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2006. [pdf] [bib] [experiments]

Erick Delage, Honglak Lee, and Andrew Y. Ng.
Automatic single-image 3d reconstructions of indoor Manhattan world scenes.
In Proceedings of the 12th International Symposium of Robotics Research (ISRR), 2005. [pdf] [bib] [experiments]

Honglak Lee and Andrew Y. Ng.
Spam deobfuscation using a hidden Markov model.
In Proceedings of the Second Conference on Email and Anti-Spam (CEAS), 2005. [pdf] [bib]
Best Student Paper Award.