Summary of Where Do Large Learning Rates Lead Us?, by Ildus Sadrtdinov et al.
Where Do Large Learning Rates Lead Us?by Ildus Sadrtdinov, Maxim Kodryan, Eduard Pokonechny, Ekaterina Lobacheva,…
Where Do Large Learning Rates Lead Us?by Ildus Sadrtdinov, Maxim Kodryan, Eduard Pokonechny, Ekaterina Lobacheva,…
Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speechby Eric Battenberg, RJ Skerry-Ryan, Daisy Stanton,…
Subgraph Aggregation for Out-of-Distribution Generalization on Graphsby Bowen Liu, Haoyang Li, Shuning Wang, Shuo Nie,…
Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Mergingby Li Shen, Anke Tang,…
Learning Infinitesimal Generators of Continuous Symmetries from Databy Gyeonghoon Ko, Hyunsu Kim, Juho LeeFirst submitted…
Evaluating K-Fold Cross Validation for Transformer Based Symbolic Regression Modelsby Kaustubh Kislay, Shlok Singh, Soham…
ReMix: Training Generalized Person Re-identification on a Mixture of Databy Timur Mamedov, Anton Konushin, Vadim…
Enhance Hyperbolic Representation Learning via Second-order Poolingby Kun Song, Ruben Solozabal, Li hao, Lu Ren,…
Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling and Zero-Shot Transferby Zihan…
Identifying Selections for Unsupervised Subtask Discoveryby Yiwen Qiu, Yujia Zheng, Kun ZhangFirst submitted to arxiv…