Schedule

This workshop will be held in-person at Mackenzie Room, Jen-Hsun Huang Engineering Center, Stanford University on April 3rd and April 4th, 2025. The session will cover invited talks, contributed lightning talks, and a panel discussion. Long invited talks span for 45 minutes, short talks for 20 minutes and contributed lightning talks for 10 minutes each. The tentative schedule in local time zone, Pacific Stanford Time (PST), can be found below.

3rd April, 2025

07:45 - 08:15 - Breakfast

08:15 - 08:30 - Welcome Note

08:30 - 09:15 — Invited talk
Speaker: Brian Trippe
Title: Generative Methods for Protein Design: Recent Progress and Open Problems

09:15 - 10:00 — Invited talk

Speaker: Ashia Wilson
Title: Two Approaches Towards Adaptive Optimization

10:00 - 10:30 — Coffee break

10:30 - 11:15 — Invited talk
Speaker: Kyunghyun Cho
Title: Causality gets Help from Deep Learning

11:15 - 12:00 — Invited talk
Speaker: David Baker
Title: Design of New Protein Functions using Deep Learning

12:00 - 13:00 — Lunch break

13:00 - 13:40 — Accepted lightning talks

Lightning talks details 13:00 - 13:10 Preferential Multi-Objective Bayesian Optimization for Drug Discovery by Tai Dang
13:10 - 13:20 Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization by Dongxia Wu
13:20 - 13:30 Diffusion Preference Optimization for Scientific Design by Minkai Xu
13:30 - 13:40 Optimizing Adaptive Experiments: A Unified Approach to Regret Minimization and Best-Arm Identification by Chao Qin

13:45 - 14:00 — Break

14:00 - 14:45 — Invited talk
Speaker: Aaron Streets
Title: Designing Multimodal Single-Cell Measurements

14:45 - 15:30 — — Invited talk
Speaker: Brian Hie
Title: Genome Modeling and Design across All Domains of Life

15:30 - 16:00 — Coffee break

16:00 - 17:00 — Accepted lightning talks

Lightning talks details 16:00 - 16:10 An AI Agent for Designing Genetic Perturbation Experiments by Yusuf Roohani
16:10 - 16:20 A Scalable Gene Network Model for Functional Insights into Single-Cell Dynamics by Paul Bertin
16:20 - 16:30 Model guided optimization of stem cell differentiation into adaptive immune cells for clinical therapies by John Edgar
16:30 - 16:40 The Importance of Implicit Semantic Context when Classifying Rare Phenomena in Large Scientific Imagery by Ellianna Abrahams
16:40 - 16:50 PerTurboAgent: A self-planning agent for boosting sequential perturb-seq experiment by Yongju Lee
16:50 - 17:00 Preference-Guided Diffusion for Multi-Objective Offline Optimization by Yashas Annadani

17:00 - 18:00 — Poster Session. Poster board assignments are provided here.

18:00 — Workshop Dinner

4th April, 2025

08:00 - 08:30 - Breakfast

08:30 - 09:15 — Invited talk
Speaker: Jure Leskovec
Title: AI Agents for Accelerating Biological Discovery: From Hypothesis Generation to Experimental Design

09:15 - 10:00 — Invited talk
Speaker: Jennifer Listgarten
Title: How AI is Shaping Protein Engineering

10:00 - 10:30 — Coffee break

10:30 - 11:15 — Invited talk
Speaker: Andreas Krause
Title: Machine learning in the Optimization and Discovery Loop

11:15 - 12:00 — Invited talk
Speaker: Yisong Yue
Title: AI for Adaptive Experimental Design

12:00 - 13:00 — Lunch break

13:00 - 13:45 — Panel discussion
Panelists: Kyunghyun Cho, Andreas Krause, Barbara Engelhardt, Ashia Wilson, Yisong Yue
Moderator: Brian Trippe

13:45 - 14:30 — Invited talk
Speaker: Adji Bousso Dieng
Title: Vendi Scoring For Experimental Design

14:30 - 15:00 — Coffee break

15:00 - 16:00 — Accepted lightning talks

Lightning talks details 15:00 - 15:10 Improving Off-Policy Evaluation with LLM-Generated Counterfactual Annotations by Aishwarya Mandyam
15:10 - 15:20 Optimizing Likelihoods via Mutual Information: Bridging Simulation-Based Inference and Bayesian Optimal Experimental Design by Vincent Zaballa
15:20 - 15:30 Diversity-based selection for best policy identification in contextual bandit settings by Hyunji (Alex) Nam
15:30 - 15:40 Practical Bayesian Algorithm Execution via Posterior Sampling by Raul Astudillo
15:40 - 15:50 Gradient Oriented Active Learning for Candidate Drug Design by Venkatesh Medabalimi
15:50 - 16:00 Aligning Protein Language Models with Continuous Feedback using Energy Rank Alignment by Sebastian Ibarraran

16:00 - 17:00 — Unstructured networking and discussion