Honglak Lee

发表

Random Encoder RL Encoder Representation Space Intrinsic Reward Policy Expected Reward Extrinsic Reward

P. Abbeel, Jinwoo Shin, Kimin Lee, 2021 .

Why Do Better Loss Functions Lead to Less Transferable Features?

Mohammad Norouzi, Simon Kornblith, Ting Chen, 2020, NeurIPS.

Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization

Jongwook Choi, Aleksandra Faust, Sungryull Sohn, 2022, UAI.

Is Continual Learning Truly Learning Representations Continually?

Hyunwoo J. Kim, Moontae Lee, Honglak Lee, 2022, ArXiv.

Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

Jongeun Choi, Honglak Lee, Hyunwoo Ryu, 2022, 2206.08321.

Few-shot Subgoal Planning with Language Models

L. Logeswaran, Moontae Lee, Honglak Lee, 2022, NAACL.

Pure Transformers are Powerful Graph Learners

Seunghoon Hong, Moontae Lee, Seonwoo Min, 2022, ArXiv.

Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

Jongeun Choi, Honglak Lee, Jeong-Hoon Lee, 2022, ArXiv.

LEPUS: Prompt-based Unsupervised Multi-hop Reranking for Open-domain QA

L. Logeswaran, Lu Wang, Moontae Lee, 2022, ArXiv.

Is Continual Learning Truly Learning Representations Continually?

Hyunwoo J. Kim, Moontae Lee, Honglak Lee, 2022, ArXiv.

Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

Jongeun Choi, Honglak Lee, Jeong-Hoon Lee, 2022, ArXiv.

Pure Transformers are Powerful Graph Learners

Seunghoon Hong, Moontae Lee, Seonwoo Min, 2022, NeurIPS.

Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks

Yijie Guo, Honglak Lee, Qiucheng Wu, 2022, AAAI.

Fully Convolutional Transformer with Local-Global Attention

Seung Hwan Kim, Honglak Lee, Janghyeon Lee, 2022, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Simple and Effective Synthesis of Indoor 3D Scenes

Jing Yu Koh, Harsh Agrawal, Dhruv Batra, 2022, AAAI Conference on Artificial Intelligence.

Pathdreamer: A World Model for Indoor Navigation pdf

Jason Baldridge, Peter Anderson, Jing Yu Koh, 2021, ALVR.

Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction pdf

Seunghoon Hong, Whie Jung, Jing Yu Koh, 2021, ICLR.

Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

Jongeun Choi, Honglak Lee, Jeong-Hoon Lee, 2022, ICLR.

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning

Sergey Levine, Jongwook Choi, Shixiang Shane Gu, 2021, ICML.

L-Verse: Bidirectional Generation Between Image and Text

Seung Hwan Kim, Honglak Lee, Kyunghoon Bae, 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Text as Neural Operator: Complex Image Manipulation by Text Instruction

Weilong Yang, Lu Jiang, Irfan Essa, 2020 .

Environment Generation for Zero-Shot Compositional Reinforcement Learning

Natasha Jaques, Aleksandra Faust, Izzeddin Gur, 2022, NeurIPS.

i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning

Jinwoo Shin, Kihyuk Sohn, Honglak Lee, 2021, ICLR.

Learning to Weight Imperfect Demonstrations

Chang Xu, Chang Xu, Honglak Lee, 2021, ICML.

Preference Transformer: Modeling Human Preferences using Transformers for RL

P. Abbeel, Jinwoo Shin, Kimin Lee, 2023, ICLR.

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning pdf

Wilka Carvalho, Sungryull Sohn, Honglak Lee, 2021, NeurIPS.

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

P. Abbeel, Jinwoo Shin, Kimin Lee, 2022, ICLR.

Batch Reinforcement Learning Through Continuation Method

Nicolas Le Roux, Ed H. Chi, Minmin Chen, 2021, ICLR.

Improving Transferability of Representations via Augmentation-Aware Self-Supervision pdf

Hankook Lee, Jinwoo Shin, Honglak Lee, 2021, NeurIPS.

Learning Parameterized Task Structure for Generalization to Unseen Entities

Anthony Z. Liu, Sungryull Sohn, Honglak Lee, 2022, AAAI.

Lipschitz-constrained Unsupervised Skill Discovery

Jaekyeom Kim, Jongwook Choi, Honglak Lee, 2022, ICLR.

Towards More Objective Evaluation of Class Incremental Learning: Representation Learning Perspective

Hyunwoo J. Kim, Moontae Lee, Honglak Lee, 2022, 2206.08101.

Scalable 3D Captioning with Pretrained Models

Honglak Lee, Justin Johnson, Honglak Lee, 2023, NeurIPS.

Composing Task Knowledge with Modular Successor Feature Approximators

Richard L. Lewis, Satinder Singh, Angelos Filos, 2023, International Conference on Learning Representations.

Learning Compositional Tasks from Language Instructions

L. Logeswaran, Honglak Lee, Wilka Carvalho, 2023, AAAI.

Composing Task Knowledge with Modular Successor Feature Approximators

Richard L. Lewis, Satinder Singh, Angelos Filos, 2023, ICLR.

Self-Imitation Learning

Satinder Singh, Honglak Lee, Junhyuk Oh, 2018, ICML.

UNSUPERVISED OBJECT INTERACTION LEARNING WITH COUNTERFACTUAL DYNAMICS MODELS

Jongwook Choi, Sungryull Sohn, Sungtae Lee, 2023 .

Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning pdf

Sergey Levine, Jongwook Choi, Shixiang Shane Gu, 2021, ArXiv.

Story Visualization by Online Text Augmentation with Context Memory

Seung Wook Kim, Honglak Lee, Dongyeop Kang, 2023, 2023 IEEE/CVF International Conference on Computer Vision (ICCV).

BRPO: Batch Residual Policy Optimization

Ed H. Chi, Craig Boutilier, Honglak Lee, 2020, International Joint Conference on Artificial Intelligence.

Contrastive Representation Learning for Rapid Intraoperative Diagnosis of Skull Base Tumors Imaged Using Stimulated Raman Histology pdf

Daniel A. Orringer, Rushikesh S. Joshi, Sandra Camelo-Piragua, 2021, ArXiv.

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

P. Abbeel, Jinwoo Shin, Kimin Lee, 2022, ArXiv.

A Picture is Worth a Thousand Words: Language Models Plan from Pixels

Anthony Z. Liu, Sungryull Sohn, Honglak Lee, 2023, ArXiv.

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks pdf

Harm van Seijen, Mehdi Fatemi, Jongwook Choi, 2021, ICML.

Exploring Demonstration Ensembling for In-context Learning

Lu Wang, Moontae Lee, Honglak Lee, 2023, ArXiv.

Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective

Hyunwoo J. Kim, Moontae Lee, Honglak Lee, 2022, 2206.08101.