arXiv subjects

Louis Béthune

Publications and source records attributed to Louis Béthune.

At least 19 recordsLinked to original sources

arXiv2026

Learning Unmasking Policies for Diffusion Language Models

Diffusion (Large) Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks, while holding the promise of being more efficient during inference. One critical design aspect of dLLMs is the sampling procedure that selects which tokens to unmask at each diffusion step. Indeed, recent work has found that heuristic strategies such as confidence thresholding improve both sample quality and token throughput compared to random unmasking. However, such heuristics have downsides: they require manual tuning, and we observe that their performance degrades with larger block sizes. In this work, we instead propose to train sampling procedures using reinforcement learning. Specifically, we formalize masked diffusion sampling as a Markov decision process in which the dLLM serves as the environment, and propose a lightweight policy based on a single-layer transformer that maps dLLM token confidences to unmasking decisions. Our experiments show that these trained policies match the performance of state-of-the-art heuristics when combined with semi-autoregressive (block) generation, while outperforming them in the full-diffusion setting.

cs.LG↗

arXiv2026

LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss

Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their parameter size. Especially the capacity of Small Language Models (SLMs) is limited, leading to factually incorrect generations. This problem is often mitigated by giving the SLM access to an outside source: the ability to query a larger model, documents, or a database. Under this setting, we study the fundamental question of \emph{which tokens an SLM can and should learn} during pretraining, versus \emph{which ones it should delegate} via a \texttt{ } token. We find that this is not simply a question of loss: although the loss is predictive of whether a predicted token mismatches the ground-truth, it is insufficient for identifying which predictions would actually lead to factual or semantically invalid continuations. Some high-loss tokens correspond to \emph{acceptable} alternative continuations of a pretraining document and therefore should not trigger a \texttt{ }. This suggests that learnability cannot be characterized from loss alone, but requires additional domain-specific signals about the role of a token in the sentence. In Wikipedia-like domains, we show that augmenting the loss signal with lightweight grammatical information from a spaCy parser substantially improves delegation decisions. Based on this insight, we propose LaCy, a novel pretraining method that combines loss with factuality signals to decide which tokens an SLM should learn. Our experiments demonstrate that LaCy models successfully learn which tokens to predict and when to call for help. This results in higher FactScores when generating in a cascade with a bigger model and outperforms Rho or LLM-judge trained SLMs, while being simpler and cheaper.

cs.CL↗

arXiv2026

Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such as high weight decay, and mixing in data from a high-resource auxiliary language to directly aid the low-resource target. While hyperparameter tuning regularizes the model by shrinking weights to restrict network capacity, auxiliary data mixing uses a tunable mixing ratio to expand the training distribution and diversify the training signal with new knowledge. Both offer a principled way to improve training in a data-constrained domain. We compare these levers systematically across four model scales from 150M to 1.43B parameters, using Arabic as the low-resource target and English as the auxiliary, over approximately 1000 pre-training runs. Three findings emerge. First, mixing yields larger improvements than hyperparameter tuning on both validation loss and downstream task accuracy, and the gap grows with model size. Second, we quantify how much mixing helps: it boosts performance by an amount equivalent to 2--3$\times$ the unique target data on validation loss and 2--13$\times$ on downstream task accuracy, with the gain scaling steeply with model size. Third, this divergence reveals that target-language validation loss systematically underestimates mixing's value. Mixing regularizes by diversifying the training signal and contributes knowledge the repeated target corpus cannot supply; validation loss captures only the first effect. Our practical recommendations are: mix in a high-resource language, prioritize the mixing ratio over hyperparameter tuning, and transfer hyperparameters from a small proxy model via $μ$P.

cs.LG↗

arXiv2026

Scaling Categorical Flow Maps

Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved for continuous modalities, including accelerated sampling and tilting. Recently, several works have demonstrated the possibility of generating discrete data continuously by a simple flow matching process between a Gaussian and the one-hot encoded data distribution. They have further shown the feasibility of accelerated sampling via Categorical Flow Maps (CFMs), resulting in competitive sample quality in the few-step regime. However, this method had only been evaluated at relatively modest scales ($<1$B), leaving the question of its scalability completely open. In this article, we train a $1.7$B-parameter base flow model on $2.1$T tokens and self-distill it into a CFM that generates diverse, high-quality text in as few as $4$ inference steps while maintaining near-data-level token entropy. Furthermore, we introduce a likelihood bound for CFMs in the semi-discrete setting, and show that they can be used to score the model on standard LM benchmarks, achieving results in the same range as discrete diffusion methods. Finally, we uncover some of the challenges that arise from training these models at scale, and we provide prescriptive insights on loss weighting and time scheduling.

cs.LG↗

arXiv2025

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration

Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works on neural network parameterisations, such as $μ$P, have enabled transfer of optimal global hyperparameters across model sizes. These works propose an empirical practice of search for optimal global base hyperparameters at a small model size, and transfer to a large size. We extend these works in two key ways. To handle scaling along most important scaling axes, we propose the Complete$^{(d)}$ Parameterisation that unifies scaling in width and depth -- using an adaptation of CompleteP -- as well as in batch-size and training duration. Secondly, with our parameterisation, we investigate per-module hyperparameter optimisation and transfer. We characterise the empirical challenges of navigating the high-dimensional hyperparameter landscape, and propose practical guidelines for tackling this optimisation problem. We demonstrate that, with the right parameterisation, hyperparameter transfer holds even in the per-module hyperparameter regime. Our study covers an extensive range of optimisation hyperparameters of modern models: learning rates, AdamW parameters, weight decay, initialisation scales, and residual block multipliers. Our experiments demonstrate significant training speed improvements in Large Language Models with the transferred per-module hyperparameters.

cs.LG↗

arXiv2025

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

What is the shortest path between two data points lying in a high-dimensional space? While the answer is trivial in Euclidean geometry, it becomes significantly more complex when the data lies on a curved manifold -- requiring a Riemannian metric to describe the space's local curvature. Estimating such a metric, however, remains a major challenge in high dimensions. In this work, we propose a method for deriving Riemannian metrics directly from pretrained Energy-Based Models (EBMs) -- a class of generative models that assign low energy to high-density regions. These metrics define spatially varying distances, enabling the computation of geodesics -- shortest paths that follow the data manifold's intrinsic geometry. We introduce two novel metrics derived from EBMs and show that they produce geodesics that remain closer to the data manifold and exhibit lower curvature distortion, as measured by alignment with ground-truth trajectories. We evaluate our approach on increasingly complex datasets: synthetic datasets with known data density, rotated character images with interpretable geometry, and high-resolution natural images embedded in a pretrained VAE latent space. Our results show that EBM-derived metrics consistently outperform established baselines, especially in high-dimensional settings. Our work is the first to derive Riemannian metrics from EBMs, enabling data-aware geodesics and unlocking scalable, geometry-driven learning for generative modeling and simulation.

cs.LG↗

arXiv2025

Improved learning theory for kernel distribution regression with two-stage sampling

The distribution regression problem encompasses many important statistics and machine learning tasks, and arises in a large range of applications. Among various existing approaches to tackle this problem, kernel methods have become a method of choice. Indeed, kernel distribution regression is both computationally favorable, and supported by a recent learning theory. This theory also tackles the two-stage sampling setting, where only samples from the input distributions are available. In this paper, we improve the learning theory of kernel distribution regression. We address kernels based on Hilbertian embeddings, that encompass most, if not all, of the existing approaches. We introduce the novel near-unbiased condition on the Hilbertian embeddings, that enables us to provide new error bounds on the effect of the two-stage sampling, thanks to a new analysis. We show that this near-unbiased condition holds for three important classes of kernels, based on optimal transport and mean embedding. As a consequence, we strictly improve the existing convergence rates for these kernels. Our setting and results are illustrated by numerical experiments.

math.ST↗

arXiv2025

Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency

The adoption of text-to-image diffusion models raises concerns over reliability, drawing scrutiny under the lens of various metrics like calibration, fairness, or compute efficiency. We focus in this work on two issues that arise when deploying these models: a lack of diversity when prompting images, and a tendency to recreate images from the training set. To solve both problems, we propose a method that coaxes the sampled trajectories of pretrained diffusion models to land on images that fall outside of a reference set. We achieve this by adding repellency terms to the diffusion SDE throughout the generation trajectory, which are triggered whenever the path is expected to land too closely to an image in the shielded reference set. Our method is sparse in the sense that these repellency terms are zero and inactive most of the time, and even more so towards the end of the generation trajectory. Our method, named SPELL for sparse repellency, can be used either with a static reference set that contains protected images, or dynamically, by updating the set at each timestep with the expected images concurrently generated within a batch, and with the images of previously generated batches. We show that adding SPELL to popular diffusion models improves their diversity while impacting their FID only marginally, and performs comparatively better than other recent training-free diversity methods. We also demonstrate how SPELL can ensure a shielded generation away from a very large set of protected images by considering all 1.2M images from ImageNet as the protected set.

cs.CV↗

arXiv2025

Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures

The canonical approach in generative modeling is to split model fitting into two blocks: define first how to sample noise (e.g. Gaussian) and choose next what to do with it (e.g. using a single map or flows). We explore in this work an alternative route that ties sampling and mapping. We find inspiration in moment measures, a result that states that for any measure $ρ$, there exists a unique convex potential $u$ such that $ρ=\nabla u \sharp e^{-u}$. While this does seem to tie effectively sampling (from log-concave distribution $e^{-u}$) and action (pushing particles through $\nabla u$), we observe on simple examples (e.g., Gaussians or 1D distributions) that this choice is ill-suited for practical tasks. We study an alternative factorization, where $ρ$ is factorized as $\nabla w^*\sharp e^{-w}$, where $w^*$ is the convex conjugate of a convex potential $w$. We call this approach conjugate moment measures, and show far more intuitive results on these examples. Because $\nabla w^*$ is the Monge map between the log-concave distribution $e^{-w}$ and $ρ$, we rely on optimal transport solvers to propose an algorithm to recover $w$ from samples of $ρ$, and parameterize $w$ as an input-convex neural network. We also address the common sampling scenario in which the density of $ρ$ is known only up to a normalizing constant, and propose an algorithm to learn $w$ in this setting.

stat.ML↗

arXiv2025

Deep Sturm--Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions

Although Artificial Neural Networks (ANNs) have achieved remarkable success across various tasks, they still suffer from limited generalization. We hypothesize that this limitation arises from the traditional sample-based (0--dimensionnal) regularization used in ANNs. To overcome this, we introduce \textit{Deep Sturm--Liouville} (DSL), a novel function approximator that enables continuous 1D regularization along field lines in the input space by integrating the Sturm--Liouville Theorem (SLT) into the deep learning framework. DSL defines field lines traversing the input space, along which a Sturm--Liouville problem is solved to generate orthogonal basis functions, enforcing implicit regularization thanks to the desirable properties of SLT. These basis functions are linearly combined to construct the DSL approximator. Both the vector field and basis functions are parameterized by neural networks and learned jointly. We demonstrate that the DSL formulation naturally arises when solving a Rank-1 Parabolic Eigenvalue Problem. DSL is trained efficiently using stochastic gradient descent via implicit differentiation. DSL achieves competitive performance and demonstrate improved sample efficiency on diverse multivariate datasets including high-dimensional image datasets such as MNIST and CIFAR-10.

cs.LG↗

arXiv2025

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop models with compositional understanding capabilities, this is not reflected yet in existing datasets which, for the most part, still use plain text to describe images. In this work, we propose a new annotation strategy, graph-based captioning (GBC) that describes an image using a labeled graph structure, with nodes of various types. The nodes in GBC are created through a two-stage process: first, identifying and describing entity nodes; second, linking these nodes by highlighting \textit{compositions} and \textit{relations} among them. Since \textit{all} GBC nodes hold plain text descriptions, GBC retains the flexibility found in natural language, but can also encode hierarchical information in its edges. We demonstrate that GBC can be produced automatically, using off-the-shelf multimodal LLMs and object detection models, by building a new dataset GBC10M that gathers GBC annotations for about 10M images of the CC12M dataset. Through CLIP training on GBC10M, we show that leveraging GBC nodes' annotations -- particularly those in composition and relation nodes -- significantly boosts the model's performance across various benchmarks compared to when other annotations are used. To further explore the opportunities provided by GBC, we also investigate the use of GBC as middleware for text-to-image generation, and show the extra benefits of incorporating the graph structure in this task. Our code and datasets are released at https://github.com/apple/ml-gbc and https://huggingface.co/graph-based-captions.

cs.CV↗

arXiv2024

Multimodal Autoregressive Pre-training of Large Vision Encoders

We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this paper, we present AIMV2, a family of generalist vision encoders characterized by a straightforward pre-training process, scalability, and remarkable performance across a range of downstream tasks. This is achieved by pairing the vision encoder with a multimodal decoder that autoregressively generates raw image patches and text tokens. Our encoders excel not only in multimodal evaluations but also in vision benchmarks such as localization, grounding, and classification. Notably, our AIMV2-3B encoder achieves 89.5% accuracy on ImageNet-1k with a frozen trunk. Furthermore, AIMV2 consistently outperforms state-of-the-art contrastive models (e.g., CLIP, SigLIP) in multimodal image understanding across diverse settings.

cs.CV↗

arXiv2024

TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes

Ensuring fairness in NLP models is crucial, as they often encode sensitive attributes like gender and ethnicity, leading to biased outcomes. Current concept erasure methods attempt to mitigate this by modifying final latent representations to remove sensitive information without retraining the entire model. However, these methods typically rely on linear classifiers, which leave models vulnerable to non-linear adversaries capable of recovering sensitive information. We introduce Targeted Concept Erasure (TaCo), a novel approach that removes sensitive information from final latent representations, ensuring fairness even against non-linear classifiers. Our experiments show that TaCo outperforms state-of-the-art methods, achieving greater reductions in the prediction accuracy of sensitive attributes by non-linear classifier while preserving overall task performance. Code is available on https://github.com/fanny-jourdan/TaCo.

cs.CL↗

arXiv2024

On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective

Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual explanations.However, Saliency Maps generated by traditional neural networks are often noisy and provide limited insights. In this paper, we demonstrate that, on the contrary, the Saliency Maps of 1-Lipschitz neural networks, learned with the dual loss of an optimal transportation problem, exhibit desirable XAI properties:They are highly concentrated on the essential parts of the image with low noise, significantly outperforming state-of-the-art explanation approaches across various models and metrics. We also prove that these maps align unprecedentedly well with human explanations on ImageNet.To explain the particularly beneficial properties of the Saliency Map for such models, we prove this gradient encodes both the direction of the transportation plan and the direction towards the nearest adversarial attack. Following the gradient down to the decision boundary is no longer considered an adversarial attack, but rather a counterfactual explanation that explicitly transports the input from one class to another. Thus, Learning with such a loss jointly optimizes the classification objective and the alignment of the gradient, i.e. the Saliency Map, to the transportation plan direction.These networks were previously known to be certifiably robust by design, and we demonstrate that they scale well for large problems and models, and are tailored for explainability using a fast and straightforward method.

cs.AI↗

arXiv2022

Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks

Lipschitz constrained networks have gathered considerable attention in the deep learning community, with usages ranging from Wasserstein distance estimation to the training of certifiably robust classifiers. However they remain commonly considered as less accurate, and their properties in learning are still not fully understood. In this paper we clarify the matter: when it comes to classification 1-Lipschitz neural networks enjoy several advantages over their unconstrained counterpart. First, we show that these networks are as accurate as classical ones, and can fit arbitrarily difficult boundaries. Then, relying on a robustness metric that reflects operational needs we characterize the most robust classifier: the WGAN discriminator. Next, we show that 1-Lipschitz neural networks generalize well under milder assumptions. Finally, we show that hyper-parameters of the loss are crucial for controlling the accuracy-robustness trade-off. We conclude that they exhibit appealing properties to pave the way toward provably accurate, and provably robust neural networks.

cs.LG↗

arXiv2022

Gaussian Processes on Distributions based on Regularized Optimal Transport

We present a novel kernel over the space of probability measures based on the dual formulation of optimal regularized transport. We propose an Hilbertian embedding of the space of probabilities using their Sinkhorn potentials, which are solutions of the dual entropic relaxed optimal transport between the probabilities and a reference measure $\mathcal{U}$. We prove that this construction enables to obtain a valid kernel, by using the Hilbert norms. We prove that the kernel enjoys theoretical properties such as universality and some invariances, while still being computationally feasible. Moreover we provide theoretical guarantees on the behaviour of a Gaussian process based on this kernel. The empirical performances are compared with other traditional choices of kernels for processes indexed on distributions.

stat.ML↗

arXiv2022

GAN Estimation of Lipschitz Optimal Transport Maps

This paper introduces the first statistically consistent estimator of the optimal transport map between two probability distributions, based on neural networks. Building on theoretical and practical advances in the field of Lipschitz neural networks, we define a Lipschitz-constrained generative adversarial network penalized by the quadratic transportation cost. Then, we demonstrate that, under regularity assumptions, the obtained generator converges uniformly to the optimal transport map as the sample size increases to infinity. Furthermore, we show through a number of numerical experiments that the learnt mapping has promising performances. In contrast to previous work tackling either statistical guarantees or practicality, we provide an expressive and feasible estimator which paves way for optimal transport applications where the asymptotic behaviour must be certified.

stat.ML↗

arXiv2020

Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs

Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry Graphs (LGGs) to represent the latent spaces of trained DNN architectures. Such graphs are obtained by connecting samples that yield similar latent representations at a given layer of the considered DNN. We then obtain a generalization score by looking at how strongly connected are samples of distinct classes in LGGs. This score allowed us to rank 3rd on the NeurIPS 2020 Predicting Generalization in Deep Learning (PGDL) competition.

cs.LG↗