Hao Liu

See Google Scholar page for a complete list.

World Model on Million-Length Video And Language With Blockwise RingAttention
Hao Liu*, Wilson Yan*, Matei Zaharia, Pieter Abbeel
Arxiv, 2024
bib | paper | code | project | tl;dr

        @article{liu2024world,
            title={World Model on Million-Length Video And Language With RingAttention
            },
            author={Liu, Hao and Yan, Wilson and Zaharia, Matei and Abbeel, Pieter},
            journal={arXiv preprint arXiv:2402.08268},
            year={2024}
        }

Ring Attention with Blockwise Transformers for Near-Infinite Context
Hao Liu, Matei Zaharia, Pieter Abbeel
International Conference on Learning Representations(ICLR), 2024
bib | paper | code | media | tl;dr

        @article{liu2023ring,
            title={Ring Attention with Blockwise Transformers for Near-Infinite Context},
            author={Liu, Hao and Zaharia, Matei and Abbeel, Pieter},
            journal={International Conference on Learning Representations(ICLR)},
            year={2024}
        }

Blockwise Parallel Transformer for Large Context Models
Hao Liu, Pieter Abbeel
Advances in Neural Information Processing Systems(NeurIPS)(Spotlight Presentation), 2023
bib | paper | code | tl;dr

        @article{liu2023blockwise,
            title={Blockwise Parallel Transformer for Large Context Models},
            author={Liu, Hao and Abbeel, Pieter},
            journal={Advances in neural information processing systems},
            year={2023}
        }

Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
Hao Liu, Wilson Yan, Pieter Abbeel
Advances in Neural Information Processing Systems(NeurIPS), 2023
bib | paper | code | tl;dr

        @article{liu2023language,
            title={Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment},
            author={Liu, Hao and Yan, Wilson and Abbeel, Pieter},
            journal={Advances in neural information processing systems},
            year={2023}
        }

Chain of Hindsight Aligns Language Models with Feedback
Hao Liu, Carmelo Sferrazza, Pieter Abbeel
International Conference on Learning Representations(ICLR), 2024
bib | paper | code | tl;dr

        @article{liu2023chain,
            title={Chain of hindsight aligns language models with feedback},
            author={Liu, Hao and Sferrazza, Carmelo and Abbeel, Pieter},
            journal={International Conference on Learning Representations(ICLR)},
            year={2024}
        }

Emergent Agentic Transformer from Chain of Hindsight Experience
Hao Liu, Pieter Abbeel
International Conference on Machine Learning(ICML), 2023
bib | paper | tl;dr

        @inproceedings{liu2023emergent,
            title={Emergent Agentic Transformer from Chain of Hindsight Experience},
            author={Liu, Hao and Abbeel, Pieter},
            booktitle={International Conference on Machine Learning},
            year={2023}
        }

Masked Autoencoding for Scalable and Generalizable Decision Making
Fangchen Liu*, Hao Liu*, Aditya Grover, Pieter Abbeel
Advances in Neural Information Processing Systems(NeurIPS), 2022
bib | paper | [code | tl;dr

        @inproceedings{liu2022masked,
            title={Masked Autoencoding for Scalable and Generalizable Decision Making},
            author={Liu, Fangchen and Liu, Hao and Grover, Aditya and Abbeel, Pieter},
            booktitle={Advances in Neural Information Processing Systems},
            year={2022}
        }

Palm up: Playing in the Latent Manifold for Unsupervised Pretraining
Hao Liu, Tom Zahavy, Volodymyr Mnih, Satinder Singh
Advances in Neural Information Processing Systems(NeurIPS), 2022
bib | paper | tl;dr

        @inproceedings{liu2022palm,
            title={Palm up: Playing in the Latent Manifold for Unsupervised Pretraining},
            author={Liu, Hao and Zahavy, Tom and Mnih, Volodymyr and Singh, Satinder},
            booktitle={Advances in Neural Information Processing Systems},
            year={2022}
        }

URLB: Unsupervised Reinforcement Learning Benchmark.
Michael Laskin, Denis Yarats, Hao Liu, Kimin Lee, Albert Zhan, Kevin Lu, Catherine Cang,
Lerrel Pinto, Pieter Abbeel
NeurIPS 2021 Track Datasets and Benchmarks, 2021
bib | paper | code | tl;dr

        @article{laskin2021urlb,
            title={URLB: Unsupervised Reinforcement Learning Benchmark},
            author={Laskin, Michael and Yarats, Denis and Liu, Hao and Lee, Kimin and Zhan, Albert and Lu, Kevin and Cang, Catherine and Pinto, Lerrel and Abbeel, Pieter},
            journal={arXiv preprint arXiv:2110.15191},
            year={2021}
        }

APS: Active Pre-Training with Successor Features
Hao Liu, Pieter Abbeel
International Conference on Machine Learning(ICML)(Long Oral Presentation), 2021.
bib | paper | code

        @inproceedings{liu2021aps,
            title={APS: Active Pre-Training with Successor Features},
            author={Liu, Hao and Abbeel, Pieter},
            booktitle={International Conference on Machine Learning},
            year={2021}
        }

Behavior From the Void: Unsupervised Active Pre-Training
Hao Liu, Pieter Abbeel
Advances in Neural Information Processing Systems(NeurIPS)(Spotlight Presentation), 2021.
bib | paper | code | tl;dr

        @inproceedings{liu2021behavior,
            title={Behavior From the Void: Unsupervised Active Pre-Training},
            author={Liu, Hao and Abbeel, Pieter},
            booktitle={Advances in Neural Information Processing Systems},
            year={2021}
        }