310 citations · 396 across the 29 of their papers we have counts for
30 papers
Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising
Youssef Saied, François Fleuret
Normalization Equivariance (NE) is a structural prior that improves robustness to distribution shift in image-to-image tasks. A function is normalization equivariant iff $f(a y…
AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression
Atul Kumar Sinha, François Fleuret
We introduce a fast low-rank factorization-based framework for compressing large language models that enables rapid compression of billion-parameter models without retraining. Unli…
Laminating Representation Autoencoders for Efficient Diffusion
Ramón Calvo-González, François Fleuret
Recent work has shown that diffusion models can generate high-quality images by operating directly on SSL patch features rather than pixel-space latents. However, the dense patch g…
The Free Transformer
François Fleuret
We propose an extension of the decoder Transformer that conditions its generative process on random latent variables which are learned without supervision thanks to a variational p…
Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners
Daniele Paliotta, Junxiong Wang, Matteo Pagliardini +6
Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common s…
Leveraging the true depth of LLMs
Ramón Calvo González, Daniele Paliotta, Matteo Pagliardini +2
The remarkable capabilities of Large Language Models (LLMs) are overshadowed by their immense computational cost. While recent work has shown that many LLM layers can be reordered…
Solvation Free Energies from Neural Thermodynamic Integration
Bálint Máté, François Fleuret, Tristan Bereau
We present a method for computing free-energy differences using thermodynamic integration with a neural network potential that interpolates between two target Hamiltonians. The int…
Efficient World Models with Context-Aware Tokenization
Vincent Micheli, Eloi Alonso, François Fleuret
Scaling up deep Reinforcement Learning (RL) methods presents a significant challenge. Following developments in generative modelling, model-based RL positions itself as a strong co…
Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
Bálint Máté, François Fleuret, Tristan Bereau
Thermodynamic integration (TI) offers a rigorous method for estimating free-energy differences by integrating over a sequence of interpolating conformational ensembles. However, TI…
Localizing Task Information for Improved Model Merging and Compression
Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez +2
Model merging and task arithmetic have emerged as promising scalable approaches to merge multiple single-task checkpoints to one multi-task model, but their applicability is reduce…
Diffusion for World Modeling: Visual Details Matter in Atari
Eloi Alonso, Adam Jelley, Vincent Micheli +4
World models constitute a promising approach for training reinforcement learning agents in a safe and sample-efficient manner. Recent world models predominantly operate on sequence…
σ-GPTs: A New Approach to Autoregressive Models
Arnaud Pannatier, Evann Courdier, François Fleuret
Autoregressive models, such as the GPT family, use a fixed order, usually left-to-right, to generate sequences. However, this is not a necessity. In this paper, we challenge this a…
Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flows
Bálint Máté, François Fleuret
We consider the problem of sampling lattice field configurations on a lattice from the Boltzmann distribution corresponding to some action. Since such densities arise as approximat…
Faster Causal Attention Over Large Sequences Through Sparse Flash Attention
Matteo Pagliardini, Daniele Paliotta, Martin Jaggi +1
Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -…
Graph Neural Networks Go Forward-Forward
Daniele Paliotta, Mathieu Alain, Bálint Máté +1
We present the Graph Forward-Forward (GFF) algorithm, an extension of the Forward-Forward procedure to graphs, able to handle features distributed over a graph's nodes. This allows…
Learning Interpolations between Boltzmann Densities
Bálint Máté, François Fleuret
We introduce a training objective for continuous normalizing flows that can be used in the absence of samples but in the presence of an energy function. Our method relies on either…
Deformations of Boltzmann Distributions
Bálint Máté, François Fleuret
Consider a one-parameter family of Boltzmann distributions . This work studies the problem of sampling from by first sampling from $p_…
The Theoretical Expressiveness of Maxpooling
Kyle Matoba, Nikolaos Dimitriadis, François Fleuret
Over the decade since deep neural networks became state of the art image classifiers there has been a tendency towards less use of max pooling: the function that takes the largest…
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas +19
Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more…
Test time Adaptation through Perturbation Robustness
Prabhu Teja Sivaprasad, François Fleuret
Data samples generated by several real world processes are dynamic in nature \textit{i.e.}, their characteristics vary with time. Thus it is not possible to train and tackle all po…
Speeding up PCA with priming
Bálint Máté, François Fleuret
We introduce primed-PCA (pPCA), a two-step algorithm for speeding up the approximation of principal components. This algorithm first runs any approximate-PCA method to get an initi…
Structural analysis of an all-purpose question answering model
Vincent Micheli, Quentin Heinrich, François Fleuret +1
Attention is a key component of the now ubiquitous pre-trained language models. By learning to focus on relevant pieces of information, these Transformer-based architectures have p…
Language Models are Few-Shot Butlers
Vincent Micheli, François Fleuret
Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal age…
Unsupervised clustering of series using dynamic programming and neural processes
Karthigan Sinnathamby, Chang-Yu Hou, Lalitha Venkataramanan +2
Following the work of arXiv:2101.09512, we are interested in clustering a given multi-variate series in an unsupervised manner. We would like to segment and cluster the series such…