96 citations · 121 across the 34 of their papers we have counts for
37 papers
A Phenomenology of Neural Geometry in Vision-Language-Action Models
Mozes Jacobs, Aiden Swann, Mathilde Papillon +16
Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it? Prior work on vision-language-action (VLA) policies establishes…
Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky
Liam Storan, Andreas Tolias, Nina Miolane
The representations that language models learn for concepts such as months, weekdays, and places display consistent geometric structure: circles and saddle-shaped "Pringle" manifol…
Look Before You Lift: Visual and Quantitative Diagnostics for Topological Deep Learning
Mathilde Papillon, Guillermo Bernárdez, Álvaro Ballón Barreiro +4
Topological deep learning (TDL) methods rely on lifting raw data into higher-order discrete domains such as simplicial complexes, cell complexes, and hypergraphs. In practice, this…
Emergent topological structure in spontaneous brain-organoid activity
Eve Bodnia, Margaux Basart, Sofie Hai +5
Neural activity is widely held to organize on low-dimensional structure embedded in a high-dimensional state space. Persistent homology reads such structure directly from the patte…
OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data
Louisa Cornelis, Johan Mathe, Louis Van Langendonck +2
Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning. Yet most benchmarks focus on the regime , where the number of graphs $n…
Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization
Franco Terranova, Guillermo Bernardez, Albert Cabellos-Aparicio +2
Graph combinatorial optimization (GCO) has attracted growing interest, as many NP-hard problems naturally admit graph formulations, yet their combinatorial explosion renders exact…
bispectrum: Selective -Bispectra Made Practical
Johan Mathe, Adele Myers, Simon Mataigne +1
Many machine learning tasks are invariant under the action of a group of transformations: signal classification can be invariant under translations, image classification under…
Sequential Group Composition: A Window into the Mechanics of Deep Learning
Giovanni Luca Marchetti, Daniel Kunin, Adele Myers +2
How do neural networks trained over sequences acquire the ability to perform structured operations, such as arithmetic, geometric, and algorithmic computation? To gain insight into…
Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor
Adele Myers Lantow, Nina Miolane
Rotation invariance is a fundamental requirement across many computer vision tasks. Historically, this inductive bias has been encoded through hand-crafted rotation-invariant repre…
GraphUniverse: Synthetic Graph Generation for Evaluating Inductive Generalization
Louis Van Langendonck, Guillermo Bernárdez, Nina Miolane +1
A fundamental challenge in graph learning is understanding how models generalize to new, unseen graphs. While synthetic benchmarks offer controlled settings for analysis, existing…
Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
Daniel Kunin, Giovanni Luca Marchetti, Feng Chen +5
What features neural networks learn, and how, remains an open question. In this paper, we introduce Alternating Gradient Flows (AGF), an algorithmic framework that describes the dy…
Unsupervised cell segmentation by fast Gaussian Processes
Laura Baracaldo, Blythe King, Haoran Yan +3
Cell boundary information is crucial for analyzing cell behaviors from time-lapse microscopy videos. Existing supervised cell segmentation tools, such as ImageJ, require tuning var…
HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations
Guillermo Bernárdez, Marco Montagna, Louis Van Langendonck +7
While Graph Neural Networks (GNNs) have proven highly effective at modeling relational data, pairwise connections cannot fully capture multi-way relationships naturally present in…
On the approximation of the Riemannian barycenter
Simon Mataigne, P. -A. Absil, Nina Miolane
We present a method for computing an approximate Riemannian barycenter of a collection of points lying on a Riemannian manifold. Our approach relies on the use of theoretically pro…
Ordered Topological Deep Learning: a Network Modeling Case Study
Guillermo Bernárdez, Miquel Ferriol-Galmés, Carlos Güemes-Palau +4
Computer networks are the foundation of modern digital infrastructure, facilitating global communication and data exchange. As demand for reliable high-bandwidth connectivity grows…
From superposition to sparse codes: interpretable representations in neural networks
David Klindt, Charles O'Neill, Patrik Reizinger +2
Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures,…
Latent computing by biological neural networks: A dynamical systems framework
Fatih Dinc, Marta Blanco-Pozo, David Klindt +8
Although individual neurons and neural populations exhibit the phenomenon of representational drift, perceptual and behavioral outputs of many neural circuits can remain stable acr…
Understanding and controlling the geometry of memory organization in RNNs
Udith Haputhanthri, Liam Storan, Yiqi Jiang +7
Training recurrent neural networks (RNNs) is a high-dimensional process that requires updating numerous parameters. Therefore, it is often difficult to pinpoint the underlying lear…
Dynamical phases of short-term memory mechanisms in RNNs
Bariscan Kurtkaya, Fatih Dinc, Mert Yuksekgonul +7
Short-term memory is essential for cognitive processing, yet our understanding of its neural mechanisms remains unclear. Neuroscience has long focused on how sequential activity pa…
When Machine Learning Gets Personal: Evaluating Prediction and Explanation
Louisa Cornelis, Guillermo Bernárdez, Haewon Jeong +1
In high-stakes domains like healthcare, users often expect that sharing personal information with machine learning systems will yield tangible benefits, such as more accurate diagn…
TopoTune : A Framework for Generalized Combinatorial Complex Neural Networks
Mathilde Papillon, Guillermo Bernárdez, Claudio Battiloro +1
Graph Neural Networks (GNNs) effectively learn from relational data by leveraging graph symmetries. However, many real-world systems -- such as biological or social networks -- fea…
ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
Guillermo Bernárdez, Lev Telyatnikov, Marco Montagna +70
This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learnin…
Bounds on the geodesic distances on the Stiefel manifold for a family of Riemannian metrics
Simon Mataigne, P. -A. Absil, Nina Miolane
We give bounds on geodesic distances on the Stiefel manifold, derived from new geometric insights. The considered geodesic distances are induced by the one-parameter family of Riem…
Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
Mathilde Papillon, Sophia Sanborn, Johan Mathe +8
The enduring legacy of Euclidean geometry underpins classical machine learning, which, for decades, has been primarily developed for data lying in Euclidean space. Yet, modern mach…