The impact of chatGPT and other large language models on physics research and education

America/New_York
32-123 (MIT)

32-123

MIT

32 Vassar St, Cambridge, MA 02139
Kevin Burdge (MIT), Joshua Borrow (Massachusetts Institute of Technology), Mark Vogelsberger (MIT)
Description

Join us for a one-day meeting within the MIT Physics Department to explore the growing significance of Language Models (LLMs). This event will feature a series of contributed talks from esteemed members of the department, along with informative overview presentations. We will delve into the practical applications of LLMs in various domains, including Teaching & Administration, Research & Writing, Programming & Data Analysis, and the underlying technology of LLMs. This gathering offers an excellent opportunity to learn, share insights, and foster collaboration within the MIT community. The event is free, and registration is open to all members of the MIT community.

The event will be hybrid, and can be attended on Zoom. The link will be sent out to registered participants before the event, and through the MIT Physics e-mail lists. If you want access the the link and have missed the registration deadline, please contact Josh Borrow (borrowj@mit.edu), listing your name, title, affiliation, and .edu e-mail.

Written by ChatGPT-3.5 (Prompt: I am organising a meeting within the MIT physics department about LLMs. The meeting will allow for contributed talks from various members of the department, and some overview talks from others. It will be a one day event. We will discuss how LLMs are relevant to Teaching & Administration, Research & Writing, Programming & Data Analysis, as well as the technology of LLMs themselves. Please write me a paragraph or two for the description of the event, mentioning it is free and registration is open to the entire MIT community. Please avoid flowery language.)

Participants
  • Abdulkadir Canatar
  • Adyant Kamdar
  • Akshit Goyal
  • Alberto Accomazzi
  • Alex Shvonski
  • Alexander Laiman
  • Alexander Rudat
  • Amer Al-Hiyasat
  • Analia Barrantes
  • Anders Lossius
  • Andrew Pochinsky
  • Andrew Vanderburg
  • André Fonseca
  • Anindita Maiti
  • Anna Golubeva
  • Anna Klales
  • Archie Tram
  • Asem Wardak
  • Atousa Kalantari
  • Avi Shporer
  • Aviram Uri
  • ayse koyun
  • Batyr Ilyas
  • Benjamin Lehmann
  • Beverly LaMarr
  • Billy Aguilar
  • Blaise Delaney
  • boxi song
  • Carlos Argüelles
  • Catherine Grant
  • Cecilia Garraffo
  • Chad Freer
  • Charlotte Loh
  • Chih-Wei Joshua Liu
  • Christoph Paus
  • Cian Roche
  • Cora Dvorkin
  • Craig Carter
  • Daniel Harlow
  • Daniel Jackson
  • Daniel Muthukrishna
  • Dave Pritchard
  • David Koplow
  • David Shoemaker
  • Deep Chatterjee
  • Deepto Chakrabarty
  • Denis Boyda
  • Dheeraj Pasham
  • Di Luo
  • Dmytro Kovalskyi
  • Edward Farhi
  • Ekaterina Govorkova
  • Eleonora Polini
  • Elyas Nasimdoust
  • Elyssa Hofgard
  • Emma Chickles
  • Eric Michaud
  • Eric Miller
  • Erin Kara
  • Erkin Verbeek
  • Fatima Zaidouni
  • Francis Huang
  • Frank Taylor
  • Frank Zhao
  • Gabor Furesz
  • Gautam Reddy
  • Ge Yang
  • George Stephans
  • Gregory Kestin
  • Gregory Prigozhin
  • Hank Stennes
  • Hillary Diane Andales
  • Hongyin Liu
  • Hope Fu
  • Hyunseok Lee
  • Ila Fiete
  • Isaac Liao
  • Isabella Macias
  • Jack Haviland
  • Jack Steiner
  • Jacqueline Hewitt
  • Jasmine Kalia
  • Jason Bessuille
  • Jeff Gore
  • Jenna Gu
  • Jiaruo Li
  • Jim Francis
  • Jinyeop Song
  • Joe Smolsky
  • Joheen Chakraborty
  • John Frank
  • John Martyn
  • John McNally
  • JOHN RICHARDSON
  • Jonas Karthein
  • Jose Marchezi
  • Joshua Bendavid
  • Joshua Borrow
  • Joshua Foster
  • Joshua Ramette
  • Josiah Sinclair
  • Julian Yocum
  • Kelly Miller
  • Krishna Rajagopal
  • Kyungseop Yoon
  • Li Du
  • Lingling Fan
  • Lisa Lin
  • Logan McCarty
  • Loyd Waites
  • Luca Lavezzo
  • Lucas Arthur
  • Lucas Ehinger
  • Ludovico Mori
  • Mads Bahrami
  • Magdelena Allen
  • Manan Agarwal
  • Manu Srivastava
  • Marianne Moore
  • Mariona Badenas
  • Mark Bautz
  • Mark Vogelsberger
  • Marti Pedemonte Bernat
  • Mason Ng
  • Matthew Cubstead
  • Matthew Peters
  • Meenakshi Sharma
  • Melbourne Tang
  • Melinda Soares
  • Melinda Soares-Furtado
  • Meredith Neyer
  • Michelle Tomasik
  • Miguel Calvo Carrera
  • Mina Bakhtiari
  • Mitchell Ostrow
  • Mohamed Abdelhafez
  • Morgane König
  • nayanika yellepeddi
  • Nicholas Rivera
  • Nick Kern
  • Nikhil Mukund
  • Ningyuan Jia
  • Nishat Fahmida Protyasha
  • Noah Chartoff
  • Or Hen
  • Orisvaldo Salviano Neto
  • Paola Cappellaro
  • Patrick Lee
  • Peter Dourmashkin
  • Peter Fisher
  • Peter Szolovits
  • Pieter Van Steenweghen
  • Quinn Castaneda
  • Rafael Martinez-Galarza
  • Riccardo Comin
  • Richard Lana
  • Rob Simcoe
  • Robert Johnston
  • RONALD GARCIA RUIZ
  • Ruixiao Yao
  • Rumen Dangovski
  • Sachin Vaidya
  • Sahil P
  • Samuel Homiller
  • Sandi Miller
  • Sean Robinson
  • Seoyeon Choi
  • Sergi Blanco-Cuaresma
  • Sheryl Barnes
  • Shuchen Zhang
  • Siddharth Mishra-Sharma
  • Silviu-Marian Udrescu
  • Steven Gordon
  • Sunghan Ro
  • Thomas Christensen
  • Thomas Hartke
  • Tzu-An Sheng
  • Vivishek Sudhir
  • Will Detmold
  • William Barletta
  • Xinghui Yin
  • Yang Zhang
  • Yepeng Huang
  • Yi Yin
  • Yifan Kang
  • Yin Lin
  • Zhangqier Wang
  • Zhilei Xu
  • Zhiren Zheng
  • Zhuo Chen
  • Ziming Liu
Kevin Burdge
    • 09:00 11:50
      The computer science underlying large language models

      This session will focus on a discussion of the computer science underlying large language models.

      Convener: Kevin Burdge (MIT)
      • 09:00
        Introductory remarks 5m
        Speaker: Dr Kevin Burdge (MIT)
      • 09:05
        Keynote address: Towards Machines that can Learn, Reason, and Plan (remote) 55m
        Speaker: Prof. Yann LeCun (NYU/Meta)
      • 10:00
        Generative AI gives some spectacular demonstrations, but I don’t know how! 15m
        Speaker: Prof. Peter Szolovits (MIT)
      • 10:15
        Language Models as World Models? 15m
        Speaker: Prof. Jacob Andreas (MIT)
      • 10:30
        Coffee Break 15m
      • 10:45
        Some experiments with LLMs, or why the world you were raised to survive in no longer exists 15m
        Speaker: Dr Siddharth Mishra-Sharma (MIT/IAIFI)
      • 11:00
        The Quantization Model of Neural Scaling 15m
        Speaker: Eric Michaud (MIT)
      • 11:15
        Keeping AI under control through mechanistic interpretability 15m
        Speaker: Prof. Max Tegmark (MIT)
      • 11:30
        Open discussion on broader societal impacts of LLMs, and implications for physics majors 20m
        Speakers: Dr Kevin Burdge (MIT), Dr Joshua Borrow (MIT)
    • 11:50 12:40
      Lunch 50m
    • 12:40 14:30
      The use of large language models in research
      • 12:40
        Collaborating with ChatGPT to train an unsupervised machine learning algorithm on astronomical data 15m
        Speaker: Emma Chickles (MIT)
      • 12:55
        Fine-Tuning LLMs for Understanding Fundamental Physics Concepts and Problems 15m
        Speaker: Rumen Dangovski (MIT)
      • 13:10
        Building a platform for understanding scientific ideas by offloading increasing amounts of the research process to AI 15m
        Speaker: Joshua Ramette (MIT)
      • 13:25
        Using natural language processing-based information to aid the detector characterization and commissioning activities at various gravitational wave observatories 15m
        Speaker: Dr Nikhil Mukund (MIT)
      • 13:40
        Interactive demo session on using chatGPT in teaching and research-type applications 10m
        Speaker: Dr Kevin Burdge (MIT)
      • 13:50
        Open discussion on use of LLMs in teaching and research 20m
        Speakers: Dr Joshua Borrow (MIT), Dr Kevin Burdge (MIT)
      • 14:10
        Coffee break 20m
    • 14:30 17:20
      The use of large language models in teaching/administration
      • 14:30
        How LLMs Are Changing Teaching at MIT 15m
        Speaker: Prof. Christopher Capozzola (MIT)
      • 14:45
        Why I’m excited (but nervous) about using GPT in my MIT teaching 15m
        Speaker: Prof. Daniel Jackson (MIT)
      • 15:00
        Combing AI transformers for convincing character generation 15m
        Speaker: Dr Loyd Hoyt Waites (MIT)
      • 15:15
        AI Augmented Support for Computing Services 15m
        Speaker: Julius Heitkoetter (MIT)
      • 15:30
        Answering student questions all-at-once! A case study for AI in the classroom 15m
        Speaker: Dr Louis Deslauriers (Harvard)
      • 15:45
        Learning the other way: on AI and acing MIT 15m
        Speaker: David Koplow (MIT)
      • 16:00
        Conversation on the Use of ChatGPT in Fall 2023 Physics Teaching 10m
        Speaker: Dr Michelle Tomasik (MIT)
      • 16:10
        Capstone talk: LLMs for Physics, and Physics for LLMs 1h
        Speaker: Dr Stephen Wolfram (Wolfram Research)
      • 17:10
        Closing remarks 5m
        Speaker: Dr Kevin Burdge (MIT)