Guannan Qu

Assistant Professor at CMU
Machine learning, control, reinforcement learning, multi-agent systems

[Dimitris Papailiopoulos @DimitrisPapail]

LLMs Can In-context Learn Multiple Tasks in Superposition

We explore a bizarre LLM superpower that allows them to solve multiple ICL tasks in parallel.

This is related to the view of them as simulators in superposition [cref:@repligate]

https://t.co/mFIUIANPF6
1/n

[Zhun Deng @zhun_deng]

I guess this announcement is a bit (or super) late. I am on the 2023-2024 faculty job market for CS and data science!! Here is my humble homepage: https://t.co/zDz92zH9Pg

[Control Meets Learning Virtual Seminars @ControlMeetsML]

Our next talk:
10/21: Tamer Başar (UIUC)

“Policy Optimization for Linear Optimal Control with Guarantees of Robustness”

Please visit https://t.co/MDhMNCa9eY…… for more information (subscribe to the Google group to receive Zoom link and future announcements).

[Control Meets Learning Virtual Seminars @ControlMeetsML]

Upcoming speakers:
Babak Hassibi (Caltech)
Tamer Başar (UIUC)
Jeff Shamma (KAUST)
Sasha Rakhlin (MIT)
Melanie Zeilinger (ETH)
Claire Tomlin (UC Berkeley)
Jean-Jacques Slotine (MIT)
Na Li (Harvard)
Marco Pavone (Stanford)

[Control Meets Learning Virtual Seminars @ControlMeetsML]

Our first talk:
09/30: Elad Hazan (Princeton) @HazanPrinceton
"The Non-Stochastic Control Problem"

Please visit https://t.co/MDhMNCa9eY for more information (subscribe to the Google group to receive Zoom link and future announcements).

[Control Meets Learning Virtual Seminars @ControlMeetsML]

We are so excited to announce a new "Control Meets Learning" virtual seminar series! Confirmed speakers include:
09/30: Elad Hazan (Princeton)
10/07: Babak Hassibi (Caltech)
TBA: Na Li (Harvard), Jeff Shamma (KAUST), Claire Tomlin (UC Berkeley), Melanie Zeilinger (ETH)