All talks listed in Pacific Time. Schedule subject to change.

–
Coffee and Check-In
–
Introduction (Sanjit Seshia)
–
Veridical Data Science towards Trustworthy AI
Bin Yu (UC Berkeley)
–
Break
–
Veridical Data Science towards Trustworthy AI
Bin Yu (UC Berkeley)
–
Lunch (on your own)
–
Provably Safe and Beneficial AI
Stuart Russell (UC Berkeley)
–
Safety of GenAI through the lens of Security and Cryptography
Somesh Jha (University of Wisconsin-Madison)
–
Break
–
Safety of GenAI through the Lens of Security and Cryptography
Somesh Jha (University of Wisconsin-Madison)
–
Reception
–
Coffee and Check-In
–
Query Languages for Machine Learning Models
Pablo Barcelo (Pontificia Universidad Catolica de Chile)
–
Symbolic Reasoning about Large Language Models
Guy van den Broeck (UCLA)
–
Break
–
Learning and decision making under observer effects
Sarah Dean (Cornell University)
–
Lunch (on your own)
–
Towards Reasoning with a Million Environment Models
Sebastian Junges (Radboud University)
–
Break
–
Automata Embeddings for Goal-Conditioned Reinforcement Learning
Beyazit Yalcinkaya (UC Berkeley)
–
Coffee and Check-In
–
Machine Teaching: Supervised Learning and Beyond
Jerry Zhu (University of Wisconsin-Madison)
–
Language Model Guided Synthesis for Lifting
Elizabeth Polgreen (University of Edinburgh)
–
Break
–
Neurosymbolic Synthesis for Trustworthy Machine Learning
Osbert Bastani (University of Pennsylvania)
–
Lunch (on your own)
–
Formal Models of Machine Teaching Without Collusion (Remote Talk)
Sandra Zilles (University of Regina)
–
Break
–
Trustworthy AI for Legal Reasoning
Ruzica Piskac (Yale University)
–
Coffee and Check-In
–
Robust Learning with Principled Out-of-Distribution Detection via Multiple Testing
Susmit Jha (SRI International)
–
Exploiting Epistemic Uncertainty for Deep Exploration in Reinforcement Learning
Matthijs Spaan (Delft University of Technology)
–
Break
–
Prediction-Powered Inference
Anastasios Angelopoulos
–
Lunch (on your own)
–
Leveraging Structure in Formal Logic-Guided Reinforcement Learning
Ameesh Shah (UC Berkeley)
–
Break
–
Shielded Reinforcement Learning
Bettina Koenighofer (Technical University of Graz)
–
Coffee and Check-In
–
AI for Safety Critical Control
Claire Tomlin (UC Berkeley)
–
Edit Distance & Robustness in (In)finite Word Languages
Dana Fisman (Ben-Gurion University)
–
Break
–
Learning and Teaching Automata via Demonstrations and Natural Languages
Marcell Vazquez-Chanlatte (Nissan Advanced Technology Center - Silicon Valley)
–
Lunch (on your own)
–
Synthesizing Pareto-optimal Interpretations of Black Box ML Models
Supratik Chakraborty (IIT Bombay)
–
Break
–
Robust Algorithmic Recourse with Predictions
Shahin Jabbari (Drexel University)