Skip to main content
Search
Utility navigation
Calendar
Contact
Login
MAKE A GIFT
Main navigation
Home
Programs & Events
Research Programs
Workshops & Symposia
Public Lectures
Research Pods
Internal Program Activities
Algorithms, Society, and the Law
People
Scientific Leadership
Staff
Current Long-Term Visitors
Research Fellows
Postdoctoral Researchers
Scientific Advisory Board
Governance Board
Industry Advisory Council
Affiliated Faculty
Science Communicators in Residence
Law and Society Fellows
Participate
Apply to Participate
Plan Your Visit
Location & Directions
Postdoctoral Research Fellowships
Law and Society Fellowships
Science Communicator in Residence Program
Circles
Breakthroughs Workshops and Goldwasser Exploratory Workshops
Support
Annual Fund
Funders
Industrial Partnerships
News & Videos
News
Videos
About
Image
Transformers as a Computational Model
Program
Special Year on Large Language Models and Transformers, Part 1
Location
Calvin Lab auditorium
Date
Monday, Sept. 23
–
Friday, Sept. 27, 2024
Back to calendar
Breadcrumb
Home
Workshop & Symposia
Schedule
Secondary tabs
The Workshop
Schedule
Videos
All talks listed in Pacific Time. Schedule subject to change.
Monday, Sept. 23, 2024
9
–
9:25 a.m.
Coffee and Check-In
9:25
–
9:30 a.m.
Opening Remarks
9:30
–
10:15 a.m.
Transformers, parallel computation, and logarithmic depth
Daniel Hsu (Columbia University)
10:15
–
10:30 a.m.
Break
10:30
–
11:15 a.m.
Capabilities and limitations of Transformer in sequential reasoning
Bingbin Liu (Carnegie Mellon University)
11:15
–
11:30 a.m.
Break
11:30 a.m.
–
12:15 p.m.
The Parallelism Tradeoff: Understanding Transformer Expressivity Through Circuit Complexity
Will Merrill (New York University)
12:15
–
2 p.m.
Lunch (on your own)
2
–
2:45 p.m.
Emergence and grokking in "simple" architectures
Misha Belkin (UCSD)
2:45
–
3 p.m.
Break
3
–
3:45 p.m.
Iterated Models: Expressive Power, Learning, and Chain of Thought
Nati Srerbo (Toyota Technological Institute at Chicago)
3:45
–
4:45 p.m.
Reception
Tuesday, Sept. 24, 2024
9
–
9:30 a.m.
Coffee and Check-In
9:30
–
10:15 a.m.
The emergence of clusters in self-attention dynamics
Philippe Rigollet (MIT)
10:15
–
10:30 a.m.
Break
10:30
–
11 a.m.
Computational Benefits and Limitations of Transformers and State-Space Models
Eran Malach (Kempner Institute, Harvard University)
11
–
11:30 a.m.
Break
11:30 a.m.
–
12:15 p.m.
Transformer Expressivity and Formal Logic
David Chiang (University of Notre Dame)
12:15
–
2 p.m.
Lunch (on your own)
2
–
2:45 p.m.
Interpretability Agents
Sarah Schwettmann (MIT)
2:45
–
3 p.m.
Break
3
–
3:45 p.m.
Recent Efficiency Improvements to Transformers
David Woodruff (Carnegie Mellon University)
3:45
–
4 p.m.
Break
4
–
5 p.m.
Panel Discussion: What can theory offer to the design and use of LLMs?
Jon Kleinberg, Philippe Rigollet, Nati Srebro, and Naomi Saphra
Wednesday, Sept. 25, 2024
9
–
9:30 a.m.
Coffee and Check-In
9:30
–
10:15 a.m.
Language Generation in the Limit
Jon Kleinberg (Cornell University)
10:15
–
10:30 a.m.
Break
10:30
–
11:15 a.m.
Do Large Language Models Perform Latent Reasoning? (Remote Talk)
Mor Geva (Tel Aviv University)
11:15
–
11:30 a.m.
Break
11:30 a.m.
–
12:15 p.m.
Language Acquisition in Language Models
Naomi Saphra (Kempner Institute at Harvard University)
12:15
–
2 p.m.
Lunch (on your own)
2
–
2:45 p.m.
What was Revolutionized by the "Transformer Revolution?
Stella Biderman (ElutherAI)
2:45
–
3 p.m.
Break
3
–
5 p.m.
Poster Session (2nd Floor Interactive Area)
Thursday, Sept. 26, 2024
9
–
9:30 a.m.
Coffee and Check-In
9:30
–
10:15 a.m.
Learning to Reason with LLMs
Noam Brown (OpenAI)
10:15
–
10:30 a.m.
Break
10:30
–
11:15 a.m.
Understanding and Improving Efficient Language Models
Simran Arora (Stanford University)
11:15
–
11:30 a.m.
Break
11:30 a.m.
–
12:15 p.m.
Using recurrence to achieve weak to strong generalization
Tom Goldstein (University of Maryland)
12:15
–
2 p.m.
Lunch (on your own)
2
–
2:45 p.m.
Towards Understanding Modern Alchemy
Ekin Akyurek (MIT)
2:45
–
3 p.m.
Break
3
–
3:45 p.m.
A Retrieval-based Language Model at Scale (Remote Talk)
Sewon Min (UC Berkeley & AI2)
3:45
–
4 p.m.
Break
4
–
5 p.m.
Panel Discussion: Are Transformers the end game?
Simran Arora, Stella Biderman, Jitendra Malik, Andrew Wilson
Friday, Sept. 27, 2024
9
–
9:30 a.m.
Coffee and Check-In
9:30
–
10:15 a.m.
On the Tradeoffs of State Space Models
Albert Gu (Carnegie Mellon University)
10:15
–
10:30 a.m.
Break
10:30
–
11:15 a.m.
Re-thinking Transformers: Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
Andrew Gordon Wilson (New York University)
11:15
–
11:30 a.m.
Break
11:30 a.m.
–
12:15 p.m.
Exact solutions to the geometric dynamics of signal propagation through transformers predict their trainability
Surya Ganguli (Stanford University)
12:15
–
2 p.m.
Lunch (on your own)
2
–
2:45 p.m.
Using Algorithms to Understand Transformers (and Using Transformers to Understand Algorithms)
Vatsal Sharan (University of Southern California)
2:45
–
3 p.m.
Break
3
–
3:45 p.m.
Associative memories as a building block in Transformers
Alberto Bietti (Flatiron Institute)
3:45
–
5 p.m.
Hike
Share this page
Copy URL of this page
link to homepage
Close
Main navigation
Home
Programs & Events
Research Programs
Workshops & Symposia
Public Lectures
Research Pods
Internal Program Activities
Algorithms, Society, and the Law
People
Scientific Leadership
Staff
Current Long-Term Visitors
Research Fellows
Postdoctoral Researchers
Scientific Advisory Board
Governance Board
Industry Advisory Council
Affiliated Faculty
Science Communicators in Residence
Law and Society Fellows
Participate
Apply to Participate
Plan Your Visit
Location & Directions
Postdoctoral Research Fellowships
Law and Society Fellowships
Science Communicator in Residence Program
Circles
Breakthroughs Workshops and Goldwasser Exploratory Workshops
Support
Annual Fund
Funders
Industrial Partnerships
News & Videos
News
Videos
About
Utility navigation
Calendar
Contact
Login
MAKE A GIFT
link to homepage
Close
Search