François Fleuret

research

∙ 06/01/2023

Faster Causal Attention Over Large Sequences Through Sparse Flash Attention

Transformer-based language models have found many diverse applications r...

0 Matteo Pagliardini, et al. ∙

research

∙ 04/21/2023

SequeL: A Continual Learning Library in PyTorch and JAX

Continual Learning is an important and challenging problem in machine le...

8 Nikolaos Dimitriadis, et al. ∙

research

∙ 02/10/2023

Graph Neural Networks Go Forward-Forward

We present the Graph Forward-Forward (GFF) algorithm, an extension of th...

0 Daniele Paliotta, et al. ∙

research

∙ 01/18/2023

Learning Deformation Trajectories of Boltzmann Densities

We introduce a training objective for continuous normalizing flows that ...

0 Bálint Máté, et al. ∙

research

∙ 11/21/2022

ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields

We present ESLAM, an efficient implicit neural representation method for...

6 Mohammad Mahdi Johari, et al. ∙

research

∙ 10/25/2022

Deformation Theory of Boltzmann Distributions

Consider a one-parameter family of Boltzmann distributions p_t(x) = 1Z_t...

0 Bálint Máté, et al. ∙

research

∙ 10/20/2022

Accurate Extrinsic Prediction of Physical Systems Using Transformers

Accurate high-altitude wind forecasting is important for air traffic con...

0 Arnaud Pannatier, et al. ∙

research

∙ 10/18/2022

Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models

In Multi-Task Learning, tasks may compete and limit the performance achi...

4 Nikolaos Dimitriadis, et al. ∙

research

∙ 09/01/2022

Transformers are Sample Efficient World Models

Deep reinforcement learning agents are notoriously sample inefficient, w...

19 Vincent Micheli, et al. ∙

research

∙ 06/14/2022

Flatten the Curve: Efficiently Training Low-Curvature Neural Networks

The highly non-linear nature of deep neural networks causes them to be s...

0 Suraj Srinivas, et al. ∙

research

∙ 05/30/2022

Flowification: Everything is a Normalizing Flow

We develop a method that can be used to turn any multi-layer perceptron ...

0 Bálint Máté, et al. ∙

research

∙ 03/07/2022

HyperMixer: An MLP-based Green AI Alternative to Transformers

Transformer-based architectures are the model of choice for natural lang...

0 Florian Mai, et al. ∙

research

∙ 03/02/2022

The Theoretical Expressiveness of Maxpooling

Over the decade since deep neural networks became state of the art image...

0 Kyle Matoba, et al. ∙

research

∙ 02/17/2022

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

Reinforcement learning competitions advance the field by providing appro...

0 Anssi Kanervisto, et al. ∙

research

∙ 02/11/2022

Borrowing from yourself: Faster future video segmentation with partial channel update

Semantic segmentation is a well-addressed topic in the computer vision l...

0 Evann Courdier, et al. ∙

research

∙ 02/10/2022

SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics

Deep learning methods have gained popularity in high energy physics for ...

10 Atul Kumar Sinha, et al. ∙

research

∙ 02/09/2022

Agree to Disagree: Diversity through Disagreement for Better Transferability

Gradient-based learning algorithms have an implicit simplicity bias whic...

0 Matteo Pagliardini, et al. ∙

research

∙ 12/20/2021

Efficient Wind Speed Nowcasting with GPU-Accelerated Nearest Neighbors Algorithm

This paper proposes a simple yet efficient high-altitude wind nowcasting...

0 Arnaud Pannatier, et al. ∙

research

∙ 11/26/2021

GeoNeRF: Generalizing NeRF with Geometry Priors

We present GeoNeRF, a generalizable photorealistic novel view synthesis ...

0 Mohammad Mahdi Johari, et al. ∙

research

∙ 10/19/2021

Test time Adaptation through Perturbation Robustness

Data samples generated by several real world processes are dynamic in na...

0 Prabhu Teja Sivaprasad, et al. ∙

research

∙ 09/08/2021

Priming PCA with EigenGame

We introduce primed-PCA (pPCA), an extension of the recently proposed Ei...

0 Bálint Máté, et al. ∙

research

∙ 04/16/2021

Language Models are Few-Shot Butlers

Pretrained language models demonstrate strong performance in most NLP ta...

0 Vincent Micheli, et al. ∙

research

∙ 04/13/2021

Structural analysis of an all-purpose question answering model

Attention is a key component of the now ubiquitous pre-trained language ...

0 Vincent Micheli, et al. ∙

research

∙ 01/26/2021

Unsupervised clustering of series using dynamic programming and neural processes

Following the work of arXiv:2101.09512, we are interested in clustering ...

11 Karthigan Sinnathamby, et al. ∙

research

∙ 01/23/2021

Unsupervised clustering of series using dynamic programming

We are interested in clustering parts of a given single multi-variate se...

11 Karthigan Sinnathamby, et al. ∙

research

∙ 10/08/2020

On the importance of pre-training data volume for compact language models

Recent advances in language modeling have led to computationally intensi...

0 Vincent Micheli, et al. ∙

research

∙ 07/09/2020

Fast Transformers with Clustered Attention

Transformers have been proven a successful model for a variety of tasks ...

34 Apoorv Vyas, et al. ∙

research

∙ 06/29/2020

Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

Transformers achieve remarkable performance in several tasks but due to ...

35 Angelos Katharopoulos, et al. ∙

research

∙ 06/25/2020

Taming GANs with Lookahead

Generative Adversarial Networks are notoriously challenging to train. Th...

12 Tatjana Chavdarova, et al. ∙

research

∙ 06/16/2020

Gradient Alignment in Deep Neural Networks

One cornerstone of interpretable deep learning is the high degree of vis...

17 Suraj Srinivas, et al. ∙

research

∙ 04/06/2020

Fair Latency-Aware Metric for real-time video segmentation networks

As supervised semantic segmentation is reaching satisfying results, many...

4 Evann Courdier, et al. ∙

research

∙ 02/08/2020

Multi-task Reinforcement Learning with a Planning Quasi-Metric

We introduce a new reinforcement learning approach combining a planning ...

55 Vincent Micheli, et al. ∙

research

∙ 10/25/2019

On the Tunability of Optimizers in Deep Learning

There is no consensus yet on the question whether adaptive gradient meth...

8 Prabhu Teja Sivaprasad, et al. ∙

research

∙ 05/03/2019

Processing Megapixel Images with Deep Attention-Sampling Models

Existing deep architectures cannot operate on very large signals such as...

26 Angelos Katharopoulos, et al. ∙

research

∙ 05/02/2019

Full-Jacobian Representation of Neural Networks

Non-linear functions such as neural networks can be locally approximated...

70 Suraj Srinivas, et al. ∙

research

∙ 04/18/2019

Reducing Noise in GAN Training with Variance Reduced Extragradient

Using large mini-batches when training generative adversarial networks (...

38 Tatjana Chavdarova, et al. ∙

research

∙ 06/05/2018

Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

End-to-end deep-learning networks recently demonstrated extremely good p...

10 Stepan Tulyakov, et al. ∙

research

∙ 03/02/2018

Not All Samples Are Created Equal: Deep Learning with Importance Sampling

Deep neural network training spends most of the computation on examples ...

0 Angelos Katharopoulos, et al. ∙

research

∙ 03/01/2018

Knowledge Transfer with Jacobian Matching

Classical distillation methods transfer representations from a "teacher"...

0 Suraj Srinivas, et al. ∙

research

∙ 02/12/2018

Geodesic Convolutional Shape Optimization

Aerodynamic shape optimization has many industrial applications. Existin...

0 Pierre Baqué, et al. ∙

research

∙ 12/06/2017

SGAN: An Alternative Training of Generative Adversarial Networks

The Generative Adversarial Networks (GANs) have demonstrated impressive ...

0 Tatjana Chavdarova, et al. ∙

research

∙ 07/28/2017

The WILDTRACK Multi-Camera Person Dataset

People detection methods are highly sensitive to the perpetual occlusion...

0 Tatjana Chavdarova, et al. ∙

research

∙ 07/03/2017

Geometric calibration of Colour and Stereo Surface Imaging System of ESA's Trace Gas Orbiter

There are many geometric calibration methods for "standard" cameras. The...

0 Stepan Tulyakov, et al. ∙

research

∙ 12/03/2016

Semi-supervised learning of deep metrics for stereo reconstruction

Deep-learning metrics have recently demonstrated extremely good performa...

0 Stepan Tulyakov, et al. ∙

research

∙ 12/02/2016

Globally Consistent Multi-People Tracking using Motion Patterns

Many state-of-the-art approaches to people tracking rely on detecting th...

0 Andrii Maksai, et al. ∙

research

∙ 11/28/2016

Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition

We present a unified framework for understanding human social behaviors ...

0 Timur Bagautdinov, et al. ∙

research

∙ 11/23/2016

Multi-Modal Mean-Fields via Cardinality-Based Clamping

Mean Field inference is central to statistical physics. It has attracted...

0 Pierre Baqué, et al. ∙

research

∙ 10/13/2016

Predicting the dynamics of 2d objects with a deep residual network

We investigate how a residual network can learn to predict the dynamics ...

0 François Fleuret, et al. ∙

research

∙ 05/23/2016

A Sub-Quadratic Exact Medoid Algorithm

We present a new algorithm, trimed, for obtaining the medoid of a set, t...

0 James Newling, et al. ∙

research

∙ 03/01/2016

Scalable Metric Learning via Weighted Approximate Rank Component Analysis

We are interested in the large-scale learning of Mahalanobis distances, ...

0 Cijo Jose, et al. ∙

François Fleuret

Featured Co-authors