Greetings from Berkeley~
The Berkeley Artificial Intelligence Research (BAIR) seminar series is hosted by the BAIR Lab and showcases dissertations and job talks of BAIR Ph.D. students and postdoctoral researchers.
These talks are held in person on the 8th floor of Berkeley Way West (BWW) at 11:10 am on Wednesdays. For those who join in person, the seminar will be followed by pizza in the kitchen of BWW8. If you are unable to attend in person, please use this link to join seminar over Zoom. (Password: 8006)
Today, Wednesday, 4/30/25's speaker is Amy Lu, a Ph.D. student, advised by Prof. Pieter Abbeel. Amy will present her dissertation.
Title: Generative Models for Real-World Drug Discovery
Abstract: Drug discovery is concerned with finding biomolecules that can treat or prevent human disease. Recent advances in deep learning for protein structure prediction and computational protein design are gaining increasing recognition, most notably with the 2024 Nobel Prize in Chemistry. What technical challenges remain between current models and real-world drug discovery? This talk examines works that aim to address this motivating question, by improving model controllability and deployability: (1) compressing the latent space of protein folding models for reusability and mechanistic understanding; (2) tackling the "co-generation" problem of simultaneously generating structure and sequence, along with a textual keyword interface for function specification; and (3) other practicalities of deploying biological foundation models, including the influence of pretraining data on task generalization and biosecurity auditing.
Bio: Amy is a PhD student in Pieter Abbeel’s group at UC Berkeley and a part‑time member of Genentech’s Prescient Design team. Her research focuses on developing and understanding generative models for drug discovery. Previously, she worked as a Student Researcher at Google Brain and an ML Engineer at Insitro, and holds a BSc and MSc from the University of Waterloo and the University of Toronto, respectively. Her research is supported in part by the NSERC PGS‑D award and D. E. Shaw Research Graduate & Postdoc Women’s Fellowship.
Wednesday seminar links: (Please do not distribute the below links beyond your organization.)
For those of you who are unable to join in person, please join via Zoom here (Password: 8006)
Unpublished Playlist of Talk Recordings
Unpublished Playlist of 2024 Recordings
Speaker Slides
Click here to add the BAIR Seminar to your calendar
Hope to see you at a seminar~
The BAIR Admin Team
The Berkeley Artificial Intelligence Research (BAIR) seminar series is hosted by the BAIR Lab and showcases dissertations and job talks of BAIR Ph.D. students and postdoctoral researchers.
These talks are held in person on the 8th floor of Berkeley Way West (BWW) at 11:10 am on Wednesdays. For those who join in person, the seminar will be followed by pizza in the kitchen of BWW8. If you are unable to attend in person, please use this link to join seminar over Zoom. (Password: 8006)
Today, Wednesday, 4/30/25's speaker is Amy Lu, a Ph.D. student, advised by Prof. Pieter Abbeel. Amy will present her dissertation.
Title: Generative Models for Real-World Drug Discovery
Abstract: Drug discovery is concerned with finding biomolecules that can treat or prevent human disease. Recent advances in deep learning for protein structure prediction and computational protein design are gaining increasing recognition, most notably with the 2024 Nobel Prize in Chemistry. What technical challenges remain between current models and real-world drug discovery? This talk examines works that aim to address this motivating question, by improving model controllability and deployability: (1) compressing the latent space of protein folding models for reusability and mechanistic understanding; (2) tackling the "co-generation" problem of simultaneously generating structure and sequence, along with a textual keyword interface for function specification; and (3) other practicalities of deploying biological foundation models, including the influence of pretraining data on task generalization and biosecurity auditing.
Bio: Amy is a PhD student in Pieter Abbeel’s group at UC Berkeley and a part‑time member of Genentech’s Prescient Design team. Her research focuses on developing and understanding generative models for drug discovery. Previously, she worked as a Student Researcher at Google Brain and an ML Engineer at Insitro, and holds a BSc and MSc from the University of Waterloo and the University of Toronto, respectively. Her research is supported in part by the NSERC PGS‑D award and D. E. Shaw Research Graduate & Postdoc Women’s Fellowship.
Wednesday seminar links: (Please do not distribute the below links beyond your organization.)
For those of you who are unable to join in person, please join via Zoom here (Password: 8006)
Unpublished Playlist of Talk Recordings
Unpublished Playlist of 2024 Recordings
Speaker Slides
Click here to add the BAIR Seminar to your calendar
Hope to see you at a seminar~
The BAIR Admin Team
Berkeley Artificial Intelligence Research (BAIR) Lab
Speaker Slides BAIR Seminar 2025