Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Honglak Lee

Honglak Lee

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

May 25, 2022
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

Figure 1 for LEPUS: Prompt-based Unsupervised Multi-hop Reranking for Open-domain QA

Figure 2 for LEPUS: Prompt-based Unsupervised Multi-hop Reranking for Open-domain QA

Figure 3 for LEPUS: Prompt-based Unsupervised Multi-hop Reranking for Open-domain QA

Figure 4 for LEPUS: Prompt-based Unsupervised Multi-hop Reranking for Open-domain QA

* 14 pages, 3 figures

Access Paper or Ask Questions

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

May 25, 2022
Sungryull Sohn, Hyunjae Woo, Jongwook Choi, lyubing qiang, Izzeddin Gur, Aleksandra Faust, Honglak Lee

Figure 1 for Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization

Figure 2 for Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization

Figure 3 for Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization

Figure 4 for Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization

* Accepted to UAI 2022 as an oral presentation

Access Paper or Ask Questions

RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects

May 14, 2022
Yunseok Jang, Ruben Villegas, Jimei Yang, Duygu Ceylan, Xin Sun, Honglak Lee

Figure 1 for RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects

Figure 2 for RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects

Figure 3 for RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects

Figure 4 for RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects

* Accepted paper at AI for Content Creation Workshop (AICC) at CVPR 2022

Access Paper or Ask Questions

Learning Parameterized Task Structure for Generalization to Unseen Entities

Mar 28, 2022
Anthony Z. Liu, Sungryull Sohn, Mahdi Qazwini, Honglak Lee

Figure 1 for Learning Parameterized Task Structure for Generalization to Unseen Entities

Figure 2 for Learning Parameterized Task Structure for Generalization to Unseen Entities

Figure 3 for Learning Parameterized Task Structure for Generalization to Unseen Entities

Figure 4 for Learning Parameterized Task Structure for Generalization to Unseen Entities

* Published in AAAI 2022

Access Paper or Ask Questions

Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution

Mar 16, 2022
Jinsu Yoo, Taehoon Kim, Sihaeng Lee, Seung Hwan Kim, Honglak Lee, Tae Hyun Kim

Figure 1 for Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution

Figure 2 for Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution

Figure 3 for Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution

Figure 4 for Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution

* 19 pages, 11 figures, preprint

Access Paper or Ask Questions

Lipschitz-constrained Unsupervised Skill Discovery

Feb 08, 2022
Seohong Park, Jongwook Choi, Jaekyeom Kim, Honglak Lee, Gunhee Kim

Figure 1 for Lipschitz-constrained Unsupervised Skill Discovery

Figure 2 for Lipschitz-constrained Unsupervised Skill Discovery

Figure 3 for Lipschitz-constrained Unsupervised Skill Discovery

Figure 4 for Lipschitz-constrained Unsupervised Skill Discovery

* Accepted to ICLR 2022

Access Paper or Ask Questions

Environment Generation for Zero-Shot Compositional Reinforcement Learning

Jan 21, 2022
Izzeddin Gur, Natasha Jaques, Yingjie Miao, Jongwook Choi, Manoj Tiwari, Honglak Lee, Aleksandra Faust

Figure 1 for Environment Generation for Zero-Shot Compositional Reinforcement Learning

Figure 2 for Environment Generation for Zero-Shot Compositional Reinforcement Learning

Figure 3 for Environment Generation for Zero-Shot Compositional Reinforcement Learning

Figure 4 for Environment Generation for Zero-Shot Compositional Reinforcement Learning

* Published in NeurIPS 2021

Access Paper or Ask Questions