Zhiting Hu
zhitinghu at gmail dot com
zhh019 at ucsd dot edu

Assistant Professor
Halıcıoğlu Data Science Institute (HDSI)
Department of Computer Science and Engineering (affiliate)
Artificial Intelligence Group (affiliate)
UC San Diego

Office: SDSC 249E

Publications  /  Google Scholar  /  Teaching  /  CV  /  Bio  /  Twitter

My primary research interests lie in the general areas of Machine Learning, Artificial Intelligence, Natural Language Processing, as well as ML systems, computer vision, healthcare, and other application domains.

In particular, I'm interested in principles and methodologies of Panoramic Learning (HDSR)—building AI agents with ALL types of experience, ranging from data instances (NeurIPS), embodied experiences (preprint), structured knowledge (ACL, NeurIPS), constraints, to rewards (EMNLP), adversaries (NeurIPS), lifelong interplay, etc. To this end, we've been studying a standardized ML formalism ("Standard Model" of ML) for systematic understanding, unifying, and generalizing a wide range of ML paradigms (e.g., supervised, unsupervised, active, reinforcement, adversarial, meta, lifelong learning). We're also building World Models (preprint-1, 2) to enable next-generation machine reasoning beyond large language models.

On this basis, I develop methods and tools for Composable ML that enable easy composition of ML solutions (LLM Reasoners, and Texar, ASYML as part of the open-source consortium CASL); and rich applications for controllable text generation (ICML) and others.

PhD

• Frederick Pi
• Jiannan Xiang
• Qiyue Gao
• Shibo Hao
• Yi Gu
• Yuheng Zha
• Bowen Tan (@CMU, with Eric Xing)

MS

• Cheng-ping Hsieh
• Jianyu Wang
• Mengqi Zhang
• Piyush Yadav
• Yi Zhang
• Yucheng Zhu

Undergrad

• Colin Wang
• Gao Mo
• Kewen Zhao
• Lechuan Wang
• Rabona Yuan Gao
• Ted Feng
• Vishvesh Bhat
• Xuhui Liu
• Yihan Wang

• 2023-12, Tutorial at NeurIPS2023 on "Language Models Meet World Models".
• 2023-06, Invited talk at ICSA2023 on "Toward a 'Standard Model' of Machine Learning" [slides].
• 2023-05, Co-organzed the ICLR2023 workshop on Machine Learning for IoT: Datasets, Perception and Understanding.
• 2023-01, Lecture at DeepLearn 2023 Winter: "A 'Standard Model' for Machine Learning with All Experience".
• 2022-10, Invited talk at MBZUAI: "Towards A 'Standard Model' of Machine Learning".
• 2022-05, Seminar at Amazon: "Machine Learning with No (Good) Data".
• 2022-04, Invited talk at USC ISI: "Text Generation with No (Good) Data: Reinforcement Learning, Causal Inference, and Unified Evaluation" [slides].
• 2021-09, Started my position at UCSD.
• 2020-09 -- present, Visiting Amazon as a scientist.
• 2021-07, Invited talks at MSR, ETH, and NUS: "Text Generation with No (Good) Data: New Reinforcement Learning and Causal Frameworks" [slides].
• 2021-07, Co-organzed the ICML2021 workshop on Machine Learning for Data.
• 2020-11, Invited talk at MPI: "Learning with ALL Experiences: A Standardized ML Formalism" [slides].
• 2020-08, Tutorial at KDD2020 on Learning from All Types of Experiences: A Unifying Machine Learning Perspective.
• 2020-02, Tutorial at AAAI2020 on Modularizing Natural Language Processing.
• 2019-12, Co-organzed the NeurIPS2019 workshop on Learning with Rich Experience: Integration of Learning Paradigms.
• show more
Co-organzed the CVPR 2019 workshop on Towards Causal, Explainable and Universal Medical Visual Diagnosis.
Co-organzed the ICML 2019 workshop on Learning and Reasoning with Graph-Structured Representations.
Released Texar, a general-purpose toolkit for ML, NLP, and text generation.
Co-organzed the ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models.

Website template from here.