The AdEMAMix Optimizer: Better, Faster, Older von Pagliardini, Matteo, Ablin, Pierre, Grangier, David

Volltext bestellen

DoGE: Domain Reweighting with Generalization Estimation von Fan, Simin, Pagliardini, Matteo, Jaggi, Martin

Volltext bestellen

CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference von Mohtashami, Amirkeivan, Pagliardini, Matteo, Jaggi, Martin

Volltext bestellen

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging von Pagliardini, Matteo, Mohtashami, Amirkeivan, Fleuret, Francois, Jaggi, Martin

Volltext bestellen

Faster Causal Attention Over Large Sequences Through Sparse Flash Attention von Pagliardini, Matteo, Paliotta, Daniele, Jaggi, Martin, Fleuret, François

Volltext bestellen

A Primal-Dual Approach to Solving Variational Inequalities with General Constraints von Chavdarova, Tatjana, Yang, Tong, Pagliardini, Matteo, Jordan, Michael I

Volltext bestellen

The AdEMAMix Optimizer: Better, Faster, Older von Pagliardini, Matteo, Ablin, Pierre, Grangier, David

Volltext

CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference von Mohtashami, Amirkeivan, Pagliardini, Matteo, Jaggi, Martin

Volltext

Agree to Disagree: Diversity through Disagreement for Better Transferability von Pagliardini, Matteo, Jaggi, Martin, Fleuret, François, Karimireddy, Sai Praneeth

Volltext bestellen

The Peril of Popular Deep Learning Uncertainty Estimation Methods von Liu, Yehao, Pagliardini, Matteo, Chavdarova, Tatjana, Stich, Sebastian U

Volltext bestellen

DoGE: Domain Reweighting with Generalization Estimation von Fan, Simin, Pagliardini, Matteo, Jaggi, Martin

Volltext

Better Word Embeddings by Disentangling Contextual n-Gram Information von Gupta, Prakhar, Pagliardini, Matteo, Jaggi, Martin

Volltext bestellen

Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features von Pagliardini, Matteo, Gupta, Prakhar, Jaggi, Martin

Volltext

A Primal-Dual Approach to Solving Variational Inequalities with General Constraints von Chavdarova, Tatjana, Yang, Tong, Pagliardini, Matteo, Jordan, Michael I

Volltext

Improving Generalization via Uncertainty Driven Perturbations von Pagliardini, Matteo, Manunza, Gilberto, Jaggi, Martin, Jordan, Michael I, Chavdarova, Tatjana

Volltext bestellen

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging von Pagliardini, Matteo, Mohtashami, Amirkeivan, Fleuret, Francois, Jaggi, Martin

Volltext

Faster Causal Attention Over Large Sequences Through Sparse Flash Attention von Pagliardini, Matteo, Paliotta, Daniele, Jaggi, Martin, Fleuret, François

Volltext

Agree to Disagree: Diversity through Disagreement for Better Transferability von Pagliardini, Matteo, Jaggi, Martin, Fleuret, François, Sai Praneeth Karimireddy

Volltext

Taming GANs with Lookahead-Minmax von Chavdarova, Tatjana, Pagliardini, Matteo, Stich, Sebastian U, Fleuret, Francois, Jaggi, Martin

Volltext bestellen

MEDITRON-70B: Scaling Medical Pretraining for Large Language Models von Chen, Zeming, Cano, Alejandro Hernández, Romanou, Angelika, Bonnet, Antoine, Matoba, Kyle, Salvi, Francesco, Pagliardini, Matteo, Fan, Simin, Köpf, Andreas, Mohtashami, Amirkeivan, Sallinen, Alexandre, Sakhaeirad, Alireza, Swamy, Vinitra, Krawczuk, Igor, Bayazit, Deniz, Marmet, Axel, Montariol, Syrielle, Hartley, Mary-Anne, Jaggi, Martin, Bosselut, Antoine

Volltext bestellen