|
BLISS Seminar
About
The BLISS seminar
is the area seminar of the Berkeley Laboratory for Information and System Sciences. Talks at the seminar cover topics including but not limited to information and coding theory, signal processing, optimization, statistics, and control. The list of talks for the current semester can be found below, and past seminars from 2016 onwards are listed here. For an archive of all talks from 1996-2015, visit the old webpage.
Spring 2025
Regular seminar time: Fridays 10 AM - 11 AM PT
Regular seminar venue: Hughes Room, 400 Cory Hall, Berkeley
subscribe to our mailing list for more details.
To give a talk at the seminar, contact Mert Cemri or Tom Courtade.
Dates marked in bold indicate that talks are at non-regular dates / times.
Recordings of the talks are available here.
Spring 2025 Schedule
| Feb 26 (Soda 510, 3pm-4pm) | Niklas Muennighoff (Stanford University) | s1: Simple test-time scaling | details |
| Mar 14 | Wuyang Chen (SFU) | PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs | details |
| Mar 31 (Simons Institute, Room 116, 2pm-3pm) | Xiangxiang Xu (MIT) | Deep Learning From an Information Perspective | details |
| Apr 18 | Berivan Isik (Google) | TBD | details |
|
|
Fall 2024 Schedule
| Oct 11 | Sandeep Pradhan (University of Michigan) | Quantum Bayesian Framework for Efficient Storage of Quantum Information | details |
| Oct 24 (Cory 400, 1pm-2pm) | Minghua Chen (City University of Hong Kong) | Machine Learning for Real-Time Constrained Optimization: The Case of Optimal Power Flow and Beyond | details |
| Oct 25 | Varun Jog (University of Cambridge) | Old problems, new perspectives: A fresh look at classical hypothesis testing | details |
| Nov 1 | Yusu Wang (UC San Diego) | Size (OOD) generalization of neural models via Algorithmic alignment | details |
| Nov 8 | Ramya Vinayak (UW-Madison) | Towards Pluralistic Alignment: Foundations for Learning Diverse Human Preferences | details |
| Nov 15 | Han Zhao (UIUC) | Revisiting Scalarization in Multi-Task Learning | details |
|
|
|