Back to Events

Seminar Series

March 05

Michael Bernstein - Generative Agents: Interactive Simulacra of Human Behavior

Michael Bernstein
Computer Science Department, Stanford University

Part Of

4:00P
- 5:00P

Location

Star (D463)
Add to Calendar 2024-03-05 16:00:00 2024-03-05 17:00:00 America/New_York Michael Bernstein - Generative Agents: Interactive Simulacra of Human Behavior Abstract:Believable proxies of human attitudes and behavior can empower applications ranging from immersive environments to social policy interventions. However, the last quarter century has seen a slow recession of human behavioral simulation as a method, in part because traditional simulations have been unable to capture the complexity and contingency of human behavior. I argue that modern artificial intelligence models allow us to re-examine this limitation. I make my case through generative agents: computational software agents that simulate believable human behavior. Generative agents enable us to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. Our generative agent architecture empowers agents to remember, reflect, and plan — enabling them to act in ways reflective of their jobs and personalities, notice and remember each other, and even plan coordinated events. Extending this line of argument, I explore how proxying human behavior and attitudes can help us design more effective online social spaces, understand the societal disagreement underlying modern AI models, and better embed societal values into our algorithms.Bio:Michael Bernstein is an Associate Professor of Computer Science at Stanford University, where he is a Bass University Fellow. His research focuses on human-computer interaction and social computing systems. This research has been reported in venues such as The New York Times, Wired, Science, and Nature, and Michael has been recognized with an Alfred P. Sloan Fellowship, UIST Lasting Impact Award, and the Computer History Museum's Patrick J. McGovern Tech for Humanity Prize. He holds a bachelor's degree in Symbolic Systems from Stanford University, as well as a master's degree and a Ph.D. in Computer Science from MIT.This talk will also be streamed over Zoom: https://mit.zoom.us/j/91879206220.Jointly sponsored by CSAIL and the Center for Collective Intelligence (CCI). Star (D463)

February 13

Tamara Munzner - Marks Revisited: Beyond Bertin

Tamara Munzner
University of British Columbia

Part Of

4:00P
- 5:00P

Location

Zoom only
Add to Calendar 2024-02-13 16:00:00 2024-02-13 17:00:00 America/New_York Tamara Munzner - Marks Revisited: Beyond Bertin Abstract:For decades, a core tenet of visualization theory has been to break down the structure of visual encodings into marks and channels: geometric marks that represent data items, whose visual appearance can be controlled by visual channels such as position, color, shape, and size. Very extensive empirical work has been carried out to characterize the expressiveness and effectiveness of these visual channels and their relative rankings, resulting in sophisticated models for how to use them. However, the situation with marks is much less well studied; researchers have continued to simply divide them into the mathematically-inspired categories of point, line, area, and volume, following proposals by Jacques Bertin dating back to the 1960s. I will present and discuss many scenarios where this conventional model falls short, in some cases even for well known chart types. I will introduce ideas about alternative models that may provide better descriptive and generative power, to resolve ambiguities and help visualization designers reason about visual encoding possibilities.Bio: Tamara Munzner is a Professor at the University of British Columbia Department of Computer Science, and holds a 2000 PhD from Stanford. She has been active in visualization research since 1991 and has published over ninety papers and chapters. She has been papers chair for IEEE InfoVis, EuroVis, and VIS, on the steering committees for InfoVis and BioVis, and the chair of the VIS Executive Committee. Her book Visualization Analysis and Design is widely used to teach visualization world-wide, and she is the co-editor of the A K Peters Visualization book series at CRC/Routledge. She received the IEEE VGTC Visualization Technical Achievement Award, multiple Test of Time Awards from InfoVis, and is an IEEE Fellow.This talk will be streamed over Zoom: https://mit.zoom.us/j/99804195917. Zoom only

February 06

Haijun Xia - Redesigning the Information Space to Unleash the Power of AI

Haijun Xia
UC San Diego

Part Of

4:00P
- 5:00P

Location

32-D463 (Star)
Add to Calendar 2024-02-06 16:00:00 2024-02-06 17:00:00 America/New_York Haijun Xia - Redesigning the Information Space to Unleash the Power of AI Abstract:When electricity was first invented, factory engineers rushed to replace steam engines with electric motors. This switch, however, made little impact on the factory's productivity due to the factories' layouts and workflows being optimized for steam power. It wasn't until thirty years later that a new generation of engineers reconfigured the layouts and workflows for electrical manufacturing, leading to a tripling of productivity. History repeats itself as we encounter a similar paradigm shift with the advent of AI. Instead of integrating AI into individual applications, my recent work explores how information spaces should be redesigned to harness AI's potential fully. In this talk, I will share some of the early work that we have been doing toward this direction. Bio:Haijun Xia is an Assistant Professor in the Cognitive Science, Design Lab, and Computer Science and Engineering at the University of California, San Diego. He also directs the Creativity Lab. His research area is Human-Computer Interaction, where he investigates several fundamental aspects of human-computer interfaces, such as information representation, interaction modality, and intent recognition. His work has received Best Paper Awards or Honorable Mentions at ACM CHI, UIST, and IEEE VIS conferences. He received his Master's and Ph.D. degrees from the Department of Computer Science, University of Toronto, and his Bachelor degree from the Department of Computer Science of Tsinghua University.This talk will also be streamed over Zoom: https://mit.zoom.us/j/91325960176. 32-D463 (Star)