firstbacksecondback
163 Results
Workshop
|
Sat 4:30 |
Spectral theory of neural prediction and alignment SueYeon Chung |
|
Workshop
|
Sat 0:15 |
Invited Talk 1: Theory on Training Dynamics of Transformers Yingbin Liang |
|
Workshop
|
Sat 6:00 |
Invited Talk 4 : Emergence of unexpected complex skills in LLMs: Some theory and experiments |
|
Workshop
|
Sat 0:00 |
Bridging the Gap Between Practice and Theory in Deep Learning Wei Chen · Christa Cuchiero · Hadi Daneshmand · Stefanie Jegelka · Zelda Mariet · Andre Niyongabo Rubungo · Jiaye Teng · Bohan Wang · Bohang Zhang · Jingzhao Zhang |
|
Workshop
|
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines Yuchen Li · Alexandre Kirchmeyer · Aashay Mehta · Yilong Qin · Boris Dadachev · Kishore Papineni · Sanjiv Kumar · Andrej Risteski |
||
Poster
|
Oracle Efficient Algorithms for Groupwise Regret Krishna Acharya · Eshwar Ram Arunachaleswaran · Sampath Kannan · Aaron Roth · Juba Ziani |
||
Poster
|
Wed 7:30 |
PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation Haopeng Sun · Lumin Xu · Sheng Jin · Ping Luo · Chen Qian · Wentao Liu |
|
Poster
|
Wed 7:30 |
The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images Nicholas Konz · Maciej Mazurowski |
|
Poster
|
Thu 1:45 |
Grokking as the transition from lazy to rich training dynamics Tanishq Kumar · Blake Bordelon · Samuel Gershman · Cengiz Pehlevan |
|
Poster
|
Fri 1:45 |
Feature Collapse Thomas Laurent · James von Brecht · Xavier Bresson |
|
Poster
|
Thu 7:30 |
Learning Optimal Contracts: How to Exploit Small Action Spaces Francesco Bacchiocchi · Matteo Castiglioni · Alberto Marchesi · Nicola Gatti |
|
Workshop
|
Measuring Sharpness in Grokking Jack Miller · Patrick Gleeson · Noam Levi · Charles O'Neill · Thang Bui |