|
Poster
|
Tue 4:30
|
MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation
Alexandre Hayderi · Amin Saberi · Ellen Vitercik · Anders Wikum
|
|
|
Workshop
|
|
MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation
Alexandre Hayderi · Amin Saberi · Ellen Vitercik · Anders Wikum
|
|
|
Workshop
|
Sat 1:00
|
Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
Cong Lu · Shengran Hu · Jeff Clune
|
|
|
Poster
|
Thu 4:30
|
Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
Andries Smit · Nathan Grinsztajn · Paul Duckworth · Thomas Barrett · Arnu Pretorius
|
|
|
Poster
|
Wed 2:30
|
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
Aaditya Singh · Ted Moskovitz · Feilx Hill · Stephanie Chan · Andrew Saxe
|
|
|
Workshop
|
Fri 8:00
|
"You just can’t go around killing people'' Explaining Agent Behavior to a Human Terminator
Uri Menkes · Ofra Amir · Assaf Hallak
|
|
|
Workshop
|
|
Can Go AIs be adversarially robust?
Tom Tseng · Euan McLean · Kellin Pelrine · Tony Wang · Adam Gleave
|
|
|
Workshop
|
|
Safer Reinforcement Learning by Going Off-policy: a Benchmark
Igor Kuznetsov
|
|
|
Workshop
|
|
"You just can’t go around killing people'' Explaining Agent Behavior to a Human Terminator
Uri Menkes · Ofra Amir · Assaf Hallak
|
|
|
Poster
|
Tue 2:30
|
Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
Justin Deschenaux · Igor Krawczuk · Grigorios Chrysos · Volkan Cevher
|
|
|
Workshop
|
|
Topological Neural Networks go Persistent, Equivariant and Continuous
Yogesh Verma · Amauri Souza · Vikas Garg
|
|
|
Poster
|
Tue 4:30
|
Let Go of Your Labels with Unsupervised Transfer
Artyom Gadetsky · Yulun Jiang · Maria Brbic
|
|
