AB
Alberto Bietti
cs.LGstat.MLcs.AIcs.CLmath.OCastro-ph.IMq-bio.BMastro-ph.COastro-ph.SRcond-mat.dis-nn
On Valency
published · living versionsW_5txyfx4z·v1 · currentpublished
Preprints & journals
52 papers in the corpus · 2016–2026Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence2606.01470v1 · Payel Mukhopadhyay, Stefan S. Nixon, Romain Watteaux et al.2026 · 0 citationsarXiv
Assign and Add: A Mechanistic Study of Compositional Arithmetic2605.31497v1 · Brady Exoo, Alberto Bietti, John Sous2026 · 0 citationsarXiv
Geometric Factual Recall in Transformers2605.12426v1 · Shauli Ravfogel, Gilad Yehudai, Joan Bruna et al.2026 · 0 citationsarXiv
Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation2605.23961v1 · Roman Klypa, Alberto Bietti, Sergei Grudinin2026 · 0 citationsarXiv
MIMIC: A Generative Multimodal Foundation Model for Biomolecules2604.24506v1 · Siavash Golkar, Jake Kovalic, Irina Espejo Morales et al.2026 · 1 citationarXiv
Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory2603.26554v2 · Juno Kim, Eshaan Nichani, Denny Wu et al.2026 · 0 citationsarXiv
Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge2603.20969v1 · Bhavya Vasudeva, Puneesh Deora, Alberto Bietti et al.2026 · 0 citationsarXiv
Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents2603.15952v2 · Jacopo Teneggi, S.M. Bargeen A. Turzo, Tanya Marwah et al.2026 · 1 citationarXiv
Representation Learning for Spatiotemporal Physical Systems2603.13227v1 · Helen Qu, Rudy Morel, Michael McCabe et al.2026 · 0 citationsarXiv
Learning to Recall with Transformers Beyond Orthogonal Embeddings.42583526 · Vural, Nuri Mert, Bietti, Alberto, Soltanolkotabi, Mahdi et al.2026 · 0 citations... International Conference on Learning Representations. 2026;2026:75057-75129
Understanding the Mechanisms of Fast Hyperparameter Transfer2512.22768v1 · Nikhil Ghosh, Denny Wu, Alberto Bietti2025 · 0 citationsarXiv
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers2512.18634v1 · Ryotaro Kawata, Yujin Song, Alberto Bietti et al.2025 · 0 citationsarXiv
Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model2511.20798v2 · Rio Alexa Fear, Payel Mukhopadhyay, Michael McCabe et al.2025 · 0 citationsarXiv
Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme2511.19390v1 · Rudy Morel, Francesco Pio Ramunno, Jeff Shen et al.2025 · 0 citationsarXiv
Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning2510.17959v2 · Jeff Shen, Francois Lanusse, Liam Holden Parker et al.2025 · 0 citationsarXiv
AION-1: Omnimodal Foundation Model for Astronomical Sciences2510.17960v1 · Liam Parker, Francois Lanusse, Jeff Shen et al.2025 · 2 citationsarXiv
Emergence of Linear Truth Encodings in Language Models2510.15804v1 · Shauli Ravfogel, Gilad Yehudai, Tal Linzen et al.2025 · 0 citationsarXiv
Learning Compositional Functions with Transformers from Easy-to-Hard Data2505.23683v1 · Zixuan Wang, Eshaan Nichani, Alberto Bietti et al.2025 · 0 citationsarXiv
BAnG: Bidirectional Anchored Generation for Conditional RNA Design2502.21274v2 · Roman Klypa, Alberto Bietti, Sergei Grudinin2025 · 1 citationProceedings of the 42nd International Conference on Machine Learning, PMLR 267:31020-31043, 2025
In-context denoising with one-layer transformers: connections between attention and associative memory retrieval2502.05164v2 · Matthew Smart, Alberto Bietti, Anirvan M. Sengupta2025 · 0 citationsarXiv
Understanding Factual Recall in Transformers via Associative Memories2412.06538v1 · Eshaan Nichani, Jason D. Lee, Alberto Bietti2024 · 0 citationsarXiv
Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers2406.03068v2 · Lei Chen, Joan Bruna, Alberto Bietti2024 · 0 citationsarXiv
Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task2406.02585v1 · Siavash Golkar, Alberto Bietti, Mariel Pettee et al.2024 · 0 citationsarXiv
Level Set Teleportation: An Optimization Perspective2403.03362v2 · Aaron Mishkin, Alberto Bietti, Robert M. Gower2024 · 0 citationsarXiv
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models2402.19449v2 · Frederik Kunstner, Robin Yadav, Alan Milligan et al.2024 · 8 citationsarXiv
Learning Associative Memories with Gradient Descent2402.18724v1 · Vivien Cabannes, Berfin Simsek, Alberto Bietti2024 · 0 citationsarXiv
On Learning Gaussian Multi-index Models with Gradient Flow2310.19793v2 · Alberto Bietti, Joan Bruna, Loucas Pillaud-Vivien2023 · 0 citationsarXiv
Scaling Laws for Associative Memories2310.02984v2 · Vivien Cabannes, Elvis Dohmatob, Alberto Bietti2023 · 0 citationsarXiv
xVal: A Continuous Numerical Tokenization for Scientific Language Models2310.02989v2 · Siavash Golkar, Mariel Pettee, Michael Eickenberg et al.2023 · 8 citationsarXiv
Multiple Physics Pretraining for Physical Surrogate Models2310.02994v2 · Michael McCabe, Bruno R'egaldo-Saint Blancard, Liam Holden Parker et al.2023 · 17 citationsarXiv
AstroCLIP: A Cross-Modal Foundation Model for Galaxies2310.03024v2 · Liam Parker, Francois Lanusse, Siavash Golkar et al.2023 · 70 citationsarXiv
Birth of a Transformer: A Memory Viewpoint2306.00802v2 · Alberto Bietti, Vivien Cabannes, Diane Bouchacourt et al.2023 · 13 citationsarXiv
The SSL Interplay: Augmentations, Inductive Bias, and Generalization2302.02774v2 · Vivien Cabannes, Bobak T. Kiani, Randall Balestriero et al.2023 · 9 citationsProceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023
On minimal variations for unsupervised representation learning2211.03782v1 · Vivien Cabannes, Alberto Bietti, Randall Balestriero2022 · 2 citationsIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, pp. 1-5,
Learning Single-Index Models with Shallow Neural Networks2210.15651v1 · Alberto Bietti, Joan Bruna, Clayton Sanford et al.2022 · 15 citationsarXiv
When does return-conditioned supervised learning work for offline reinforcement learning?2206.01079v3 · David Brandfonbrener, Alberto Bietti, Jacob Buckman et al.2022 · 13 citationsarXiv
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes2203.11864v2 · Elvis Dohmatob, Alberto Bietti2022 · 1 citationarXiv
Efficient Kernel UCB for Contextual Bandits2202.05638v1 · Houssam Zenati, Alberto Bietti, Eustache Diemert et al.2022 · 1 citationarXiv
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning2202.05318v2 · Alberto Bietti, Chen-Yu Wei, Miroslav Dud'ik et al.2022 · 24 citationsarXiv
Dual Training of Energy-Based Models with Overparametrized Shallow Neural Networks2107.05134v2 · Carles Domingo-Enrich, Alberto Bietti, Marylou Gabri'e et al.2021 · 1 citationarXiv
On the Sample Complexity of Learning under Invariance and Geometric Stability2106.07148v2 · Alberto Bietti, Luca Venturi, Joan Bruna2021 · 0 citationsarXiv
On the Universality of Graph Neural Networks on Large Random Graphs2105.13099v2 · Nicolas Keriven, Alberto Bietti, Samuel Vaiter2021 · 5 citationsarXiv
On Energy-Based Models with Overparametrized Shallow Neural Networks2104.07531v2 · Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden et al.2021 · 5 citationsarXiv
Approximation and Learning with Deep Convolutional Models: a Kernel Perspective2102.10032v3 · Alberto Bietti2021 · 7 citationsarXiv
Deep Equals Shallow for ReLU Networks in Kernel Regimes2009.14397v4 · Alberto Bietti, Francis Bach2020 · 24 citationsarXiv
Convergence and Stability of Graph Convolutional Networks on Large Random Graphs2006.01868v2 · Nicolas Keriven, Alberto Bietti, Samuel Vaiter2020 · 33 citationsarXiv
Counterfactual Learning of Stochastic Policies with Continuous Actions2004.11722v7 · Houssam Zenati, Alberto Bietti, Matthieu Martin et al.2020 · 1 citationarXiv
On the Inductive Bias of Neural Tangent Kernels1905.12173v2 · Alberto Bietti, Julien Mairal2019 · 119 citationsarXiv
A Kernel Perspective for Regularizing Deep Neural Networks1810.00363v4 · Alberto Bietti, Gr'egoire Mialon, Dexiong Chen et al.2018 · 42 citationsarXiv
A Contextual Bandit Bake-off1802.04064v5 · Alberto Bietti, Alekh Agarwal, John Langford2018 · 65 citationsarXiv
Career total: 66 works. 52 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.