Matteo Pagliardini

10 papers · 2018–2025 · 4 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (7) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge 👑 Triple Crown 💎 Century Club (10)

Conferences

ICLR (5) NAACL (2) NIPS (2) ICML (1)

Top co-authors

Martin Jaggi (8) Francois Fleuret (4) Prakhar Gupta (2) Tatjana Chavdarova (2) Amirkeivan Mohtashami (2) Daniele Paliotta (1) Simin Fan (1) David Grangier (1) Tong Yang (1) Sebastian U Stich (1)

Keywords

unsupervised learning (1) transformer architecture (1) representation learning (1) contextual information (1) semantic representation (1) neural network optimization (1) memory efficiency (1) distributed representation (1) sparse attention (1) flash attention (1) information flow (1) word embedding (1) sentence embedding (1) n-gram embedding (1) long sequence (1) n-gram feature (1) dynamic sparsity (1) unigram embedding (1) depth weighted averaging (1)

Papers

The AdEMAMix Optimizer: Better, Faster, Older ICLR 2025

CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference ICLR 2025

DOGE: Domain Reweighting with Generalization Estimation ICML 2024

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging NIPS 2024

A Primal-Dual Approach to Solving Variational Inequalities with General Constraints ICLR 2024

Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention NIPS 2023

Agree to Disagree: Diversity through Disagreement for Better Transferability ICLR 2023

Taming GANs with Lookahead-Minmax ICLR 2021

Better Word Embeddings by Disentangling Contextual n-Gram Information NAACL 2019

Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features NAACL 2018