Bo Han

Teaching

Courses

• COMP7250(PG): Machine Learning, Spring 2027

• COMP3065(UG): AI Application Development, Spring 2027

• COMP7160(PG): Research Methods in Computer Science, Autumn 2026

• COMP7250(PG): Machine Learning, Spring 2026

• COMP3065(UG): AI Application Development, Spring 2026

• SCIE3005(UG): AI for Science, Summer 2025

• COMP7250(PG): Machine Learning, Spring 2025

• COMP7160(PG): Research Methods in Computer Science, Autumn 2024

• COMP3057(UG): Intro to AI and Machine Learning, Autumn 2024

• COMP7250(PG): Machine Learning, Spring 2024

• COMP7160(PG): Research Methods in Computer Science, Autumn 2023

• COMP3057(UG): Intro to AI and Machine Learning, Autumn 2023

• COMP7250(PG): Machine Learning, Spring 2023

• COMP7180(PG): Quantitative Methods for DAAI, Autumn 2022

• COMP7160(PG): Research Methods in Computer Science, Autumn 2022

• COMP3057(UG): Intro to AI and Machine Learning, Autumn 2022

• COMP7250(PG): Machine Learning, Spring 2022

• COMP7160(PG): Research Methods in Computer Science, Autumn 2021

• COMP3057(UG): Intro to AI and Machine Learning, Autumn 2021

• COMP7250(PG): Machine Learning, Spring 2021

• COMP4015(UG): AI and Machine Learning, Autumn 2020

• COMP7250(PG): Machine Learning, Spring 2020

Tutorials

• AAAI 2026: Trustworthy Machine Reasoning with Foundation Models [Website] [Slides]

• AAAI 2026: When AI "Forgets" for Good: The Science and Practice of Machine Unlearning for AI Safety [Slides]

• AAAI 2026: Handling Out-of-Distribution Data in the Open World: Principles and Practice for Reliable AI [Slides]

• PAKDD 2026: Trustworthy and Efficient Machine Reasoning with Foundation Models [Website] [Slides]

• WWW 2025: Trustworthy AI under Imperfect Web Data [Slides]

• VALSE 2025: Trustworthy Machine Learning under Imperfect Data [Slides] [Video]

• AAAI 2024: Trustworthy Machine Learning under Imperfect Data [Website] [Slides]

• IJCAI 2024: Trustworthy Machine Learning under Imperfect Data [Slides]

• ECML 2024: Trustworthy Machine Learning under Imperfect Data

• ACML 2023: Trustworthy Learning under Imperfect Data

• CIKM 2022: Learning and Mining with Noisy Labels

• IJCAI 2021: Learning with Noisy Supervision

• ACML 2021: Learning under Noisy Supervision

• ACML 2019: Towards Noisy Supervision: Problems, Theories, and Algorithms

Lectures

• MLSS 2027: Trustworthy Machine Learning from Data to Models [PDF]

• DeepLearn 2026: Trustworthy Machine Learning from Data to Models [Website] [PDF]

• ESSAI 2026: Trustworthy Machine Learning from Data to Models [Website] [PDF]

• ACM 2026 Distinguished Lecture: Trustworthy Foundation Models [Slides]

• VALSE 2026 Annual Lecture: Trustworthy Foundation Models [Slides]

• VALSE 2026 Webinar Lecture: Trustworthy Foundation Models [Slides] [Video]

• UTokyo 2026 Guest Lecture: Trustworthy Foundation Models [Slides]

• INNS 2025 Webinar Lecture: Trustworthy Foundation Models [Slides] [Video]

Talks and Keynotes

• NeurIPS'26 Workshop: Trustworthy ML Systems for Deep Agentic Reasoning and Evaluating Open Agents [Keynote]

• THU Institute for AI Conference: Trustworthy ML Systems for Deep Agentic Reasoning and Evaluating Open Agents

• ECCV'26 Workshop: Trustworthy ML Systems for Deep Agentic Reasoning and Evaluating Open Agents [Keynote]

• WSL'26 Workshop: Trustworthy ML Systems for Deep Agentic Reasoning and Evaluating Open Agents

• HKUST(GZ) AI Workshop: Trustworthy ML Systems for Deep Agentic Reasoning and Evaluating Open Agents

• ICLR'26 AI TIME Lecture: Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning [Keynote]

• SFU AI Seminar: Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning

• UBC TrustML Workshop: Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning

• CVPR'25 Workshop: Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning [Keynote]

• USYD SAIC Lecture: Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning [AI Distinguished Lecture]

• UTS AAII Seminar: Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning

• NTU CCDS Seminar: Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning

• NUS ECE Seminar: Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning

• NeurIPS'24 Workshop: Exploring Trustworthy Foundation Models under Imperfect Data [Keynote]

• IJCAI'24 Workshop: Exploring Trustworthy Machine Learning under Imperfect Data [Keynote]

• NJU AI Seminar: Exploring Trustworthy Foundation Models under Imperfect Data

• HKBU-RIKEN AIP Joint Workshop: Exploring Trustworthy Foundation Models under Imperfect Data

• HKUST CSE Seminar: Exploring Trustworthy Machine Learning under Imperfect Data

• HKU ECE Seminar: Exploring Trustworthy Machine Learning under Imperfect Data

• IBM Research Seminar: Towards Trustworthy Learning and Reasoning under Noisy Data

• MBZUAI MLD Seminar: Towards Trustworthy Learning and Reasoning under Noisy Data

• ACCV'22 Workshop: Towards Trustworthy Learning and Reasoning under Noisy Data [Keynote]

• HKBU-NVIDIA Joint Symposium: Towards Trustworthy Learning and Reasoning under Noisy Data

• MSRA StarTrack Forum: Trustworthy Representation Learning: A Synergistic Tale of Labels, Examples and Beyond

• BAAI Qingyuan Seminar: Trustworthy Representation Learning: A Synergistic Tale of Labels, Examples and Beyond

• RIKEN AIP Seminar: Trustworthy Representation Learning: A Synergistic Tale of Labels, Examples and Beyond

• CUHK CSE Seminar: Robust Deep Learning with Noisy Labels

• NUS-RIKEN AIP Joint Workshop: Robust Deep Learning with Noisy Labels