Stéphane d'Ascoli

36 papers A* 10Journal 24Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Brain-to-Text Decoding: A Non-invasive Approach via Typing. CoRR Jarod Lévy, Mingfang Zhang, Svetlana Pinet, Jérémy Rapin, Hubert J. Banville, Stéphane d'Ascoli, Jean-Rémi King
2025	J	`jnl`	Scaling and context steer LLMs along the same computational path as the human brain. CoRR Joséphine Raugel, Stéphane d'Ascoli, Jérémy Rapin, Valentin Wyart, Jean-Rémi King
2025	J	`jnl`	Scaling laws for decoding images from brain activity. CoRR Hubert J. Banville, Yohann Benchetrit, Stéphane d'Ascoli, Jérémy Rapin, Jean-Rémi King
2025	J	`jnl`	TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction. CoRR Stéphane d'Ascoli, Jérémy Rapin, Yohann Benchetrit, Hubert J. Banville, Jean-Rémi King
2024	A*	`conf`	A Polar coordinate system represents syntax in large language models. NeurIPS Pablo Diego-Simón, Stéphane d'Ascoli, Emmanuel Chemla, Yair Lakretz, Jean-Remi King
2024	J	`jnl`	A polar coordinate system represents syntax in large language models. CoRR Pablo Diego-Simón, Stéphane d'Ascoli, Emmanuel Chemla, Yair Lakretz, Jean-Rémi King
2024	J	`jnl`	Decoding individual words from non-invasive brain recordings across 723 participants. CoRR Stéphane d'Ascoli, Corentin Bel, Jérémy Rapin, Hubert J. Banville, Yohann Benchetrit, Christophe Pallier, Jean-Rémi King
2024	—	`conf`	Elucidating the Hierarchical Nature of Behavior with Masked Autoencoders. ECCV (64) Lucas Stoffl, Andy Bonnetto, Stéphane d'Ascoli, Alexander Mathis
2024	A*	`conf`	ODEFormer: Symbolic Regression of Dynamical Systems with Transformers. ICLR Stéphane d'Ascoli, Sören Becker, Philippe Schwaller, Alexander Mathis, Niki Kilbertus
2023	J	`jnl`	Boolformer: Symbolic Regression of Logic Functions with Transformers. CoRR Stéphane d'Ascoli, Samy Bengio, Josh M. Susskind, Emmanuel Abbe
2023	J	`jnl`	Length Generalization in Arithmetic Transformers. CoRR Samy Jelassi, Stéphane d'Ascoli, Carles Domingo-Enrich, Yuhuai Wu, Yuanzhi Li, François Charton
2023	J	`jnl`	ODEFormer: Symbolic Regression of Dynamical Systems with Transformers. CoRR Stéphane d'Ascoli, Sören Becker, Alexander Mathis, Philippe Schwaller, Niki Kilbertus
2022	J	`jnl`	Deep Symbolic Regression for Recurrent Sequences. CoRR Stéphane d'Ascoli, Pierre-Alexandre Kamienny, Guillaume Lample, François Charton
2022	A*	`conf`	Deep symbolic regression for recurrence prediction. ICML Stéphane d'Ascoli, Pierre-Alexandre Kamienny, Guillaume Lample, François Charton
2022	A*	`conf`	End-to-end Symbolic Regression with Transformers. NeurIPS Pierre-Alexandre Kamienny, Stéphane d'Ascoli, Guillaume Lample, François Charton
2022	J	`jnl`	End-to-end symbolic regression with transformers. CoRR Pierre-Alexandre Kamienny, Stéphane d'Ascoli, Guillaume Lample, François Charton
2022	J	`jnl`	Optimal learning rate schedules in high-dimensional non-convex optimization problems. CoRR Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli
2021	A*	`conf`	Align, then memorise: the dynamics of learning with feedback alignment. ICML Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt
2021	A*	`conf`	ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases. ICML Stéphane d'Ascoli, Hugo Touvron, Matthew L. Leavitt, Ari S. Morcos, Giulio Biroli, Levent Sagun
2021	J	`jnl`	ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases. CoRR Stéphane d'Ascoli, Hugo Touvron, Matthew L. Leavitt, Ari S. Morcos, Giulio Biroli, Levent Sagun
2021	J	`jnl`	More data or more parameters? Investigating the effect of data structure on generalization. CoRR Stéphane d'Ascoli, Marylou Gabrié, Levent Sagun, Giulio Biroli
2021	A*	`conf`	On the interplay between data structure and loss function in classification problems. NeurIPS Stéphane d'Ascoli, Marylou Gabrié, Levent Sagun, Giulio Biroli
2021	J	`jnl`	Transformed CNNs: recasting pre-trained convolutional layers with self-attention. CoRR Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Ari Morcos
2020	—	`conf`	Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems. SLSP Stéphane d'Ascoli, Alice Coucke, Francesco Caltagirone, Alexandre Caulier, Marc Lelarge
2020	J	`jnl`	Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems. CoRR Stéphane d'Ascoli, Alice Coucke, Francesco Caltagirone, Alexandre Caulier, Marc Lelarge
2020	J	`jnl`	Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime. CoRR Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli, Florent Krzakala
2020	A*	`conf`	Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime. ICML Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli, Florent Krzakala
2020	J	`jnl`	The dynamics of learning with feedback alignment. CoRR Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt
2020	J	`jnl`	Triple descent and the two kinds of overfitting: Where & why do they appear? CoRR Stéphane d'Ascoli, Levent Sagun, Giulio Biroli
2020	A*	`conf`	Triple descent and the two kinds of overfitting: where & why do they appear? NeurIPS Stéphane d'Ascoli, Levent Sagun, Giulio Biroli
2019	J	`jnl`	Conditioned Query Generation for Task-Oriented Dialogue Systems. CoRR Stéphane d'Ascoli, Alice Coucke, Francesco Caltagirone, Alexandre Caulier, Marc Lelarge
2019	A*	`conf`	Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias. NeurIPS Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Joan Bruna
2019	J	`jnl`	Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias. CoRR Stéphane d'Ascoli, Levent Sagun, Joan Bruna, Giulio Biroli
2019	J	`jnl`	Scaling description of generalization with number of parameters in deep learning. CoRR Mario Geiger, Arthur Jacot, Stefano Spigler, Franck Gabriel, Levent Sagun, Stéphane d'Ascoli, Giulio Biroli, Clément Hongler, Matthieu Wyart
2018	J	`jnl`	A jamming transition from under- to over-parametrization affects loss landscape and generalization. CoRR Stefano Spigler, Mario Geiger, Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Matthieu Wyart
2018	J	`jnl`	The jamming transition as a paradigm to understand the loss landscape of deep neural networks. CoRR Mario Geiger, Stefano Spigler, Stéphane d'Ascoli, Levent Sagun, Marco Baity-Jesi, Giulio Biroli, Matthieu Wyart