BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Thomas Laurent

Thomas Laurent appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Machine Learningmath.OCmath.APSoftware Engineeringastro-ph.IMComputation and Languagecs.CYGenomicsmath.STNeural and Evolutionary Computingphysics.soc-phSocial and Information NetworksStatistics Theory

Catalog footprint

What is connected

21works
13topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

21 published item(s)

preprint2026arXiv

Composable Crystals: Controllable Materials Discovery via Concept Learning

De novo crystal generation, a central task in materials discovery, aims to generate crystals that are simultaneously valid, stable, unique, and novel. Existing methods mainly rely on black-box stochastic sampling, providing limited control over how generated structures move beyond the observed distribution. In this paper, we introduce a concept-based compositional framework for crystal generation. We train a vector-quantized variational autoencoder to automatically discover a shared set of reusable crystal concepts, which serve as building blocks for guided generation. These learned concepts naturally exhibit interpretability from both local atomic environments and global symmetry patterns, and generalize to crystals from different distributions. By recombining such concepts, our framework enables controllable exploration of novel crystals beyond the training distribution, rather than relying solely on unconstrained random sampling. To further improve composition efficiency, we introduce a composition generator and iteratively refine it using high-quality samples generated by the model itself. The resulting concept compositions are then used to condition downstream crystal generation. Numerical experiments on MP-20 and Alex-MP-20 show that compositing concepts separately increase base model up to 53.2% and 51.7% on V.S.U.N metric, with particular gains in novelty.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement

De novo crystal generation seeks to discover materials that are not merely realistic, but also stable and novel. However, most existing generative models are trained to maximize the likelihood of observed crystals, which encourages samples to stay close to known materials yet not necessarily align with the criteria that matter in discovery. Through an empirical investigation, we show that current crystal generative models are caught in a pronounced stability--novelty trade-off: moving toward the observed distribution preserves stability but limits novelty, whereas moving away from it quickly destroys stability. This suggests that the useful region for discovering crystals that are both stable and novel is extremely narrow. To escape the trade-off, we introduce Crys-JEPA, a joint embedding predictive architecture for crystals that learns an energy-aware latent space preserving formation-energy differences. In this space, stability assessment can be reformulated as an embedding-based comparison against accessible training crystals, reducing the reliance on expensive energy evaluation and task-specific external references. Building on Crys-JEPA, we further develop a screening-and-refinement pipeline that identifies promising generated crystals and reintroduces them to refine the generative model. On MP-20 and Alex-MP-20 datasets, we achieve improvements over baselines up to 81.4% and 82.6% on V.S.U.N metric, respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Graph Neural Networks with Learnable Structural and Positional Representations

Graph neural networks (GNNs) have become the standard learning architectures for graphs. GNNs have been applied to numerous domains ranging from quantum chemistry, recommender systems to knowledge graphs and natural language processing. A major issue with arbitrary graphs is the absence of canonical positional information of nodes, which decreases the representation power of GNNs to distinguish e.g. isomorphic nodes and other graph symmetries. An approach to tackle this issue is to introduce Positional Encoding (PE) of nodes, and inject it into the input layer, like in Transformers. Possible graph PE are Laplacian eigenvectors. In this work, we propose to decouple structural and positional representations to make easy for the network to learn these two essential properties. We introduce a novel generic architecture which we call LSPE (Learnable Structural and Positional Encodings). We investigate several sparse and fully-connected (Transformer-like) GNNs, and observe a performance increase for molecular datasets, from 1.79% up to 64.14% when considering learnable PE for both GNN classes.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning the Travelling Salesperson Problem Requires Rethinking Generalization

End-to-end training of neural network solvers for graph combinatorial optimization problems such as the Travelling Salesperson Problem (TSP) have seen a surge of interest recently, but remain intractable and inefficient beyond graphs with few hundreds of nodes. While state-of-the-art learning-driven approaches for TSP perform closely to classical solvers when trained on trivially small sizes, they are unable to generalize the learnt policy to larger instances at practical scales. This work presents an end-to-end neural combinatorial optimization pipeline that unifies several recent papers in order to identify the inductive biases, model architectures and learning algorithms that promote generalization to instances larger than those seen in training. Our controlled experiments provide the first principled investigation into such zero-shot generalization, revealing that extrapolating beyond training data requires rethinking the neural combinatorial optimization pipeline, from network layers and learning paradigms to evaluation protocols. Additionally, we analyze recent advances in deep learning for routing problems through the lens of our pipeline and provide new directions to stimulate future research.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning to Untangle Genome Assembly with Graph Convolutional Networks

A quest to determine the complete sequence of a human DNA from telomere to telomere started three decades ago and was finally completed in 2021. This accomplishment was a result of a tremendous effort of numerous experts who engineered various tools and performed laborious manual inspection to achieve the first gapless genome sequence. However, such method can hardly be used as a general approach to assemble different genomes, especially when the assembly speed is critical given the large amount of data. In this work, we explore a different approach to the central part of the genome assembly task that consists of untangling a large assembly graph from which a genomic sequence needs to be reconstructed. Our main motivation is to reduce human-engineered heuristics and use deep learning to develop more generalizable reconstruction techniques. Precisely, we introduce a new learning framework to train a graph convolutional network to resolve assembly graphs by finding a correct path through them. The training is supervised with a dataset generated from the resolved CHM13 human sequence and tested on assembly graphs built using real human PacBio HiFi reads. Experimental results show that a model, trained on simulated graphs generated solely from a single chromosome, is able to remarkably resolve all other chromosomes. Moreover, the model outperforms hand-crafted heuristics from a state-of-the-art \textit{de novo} assembler on the same graphs. Reconstructed chromosomes with graph networks are more accurate on nucleotide level, report lower number of contigs, higher genome reconstructed fraction and NG50/NGA50 assessment metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Long-Tailed Learning Requires Feature Learning

We propose a simple data model inspired from natural data such as text or images, and use it to study the importance of learning features in order to achieve good generalization. Our data model follows a long-tailed distribution in the sense that some rare subcategories have few representatives in the training set. In this context we provide evidence that a learner succeeds if and only if it identifies the correct features, and moreover derive non-asymptotic generalization error bounds that precisely quantify the penalty that one must pay for not learning features.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The Forgotten Margins of AI Ethics

How has recent AI Ethics literature addressed topics such as fairness and justice in the context of continued social and structural power asymmetries? We trace both the historical roots and current landmark work that have been shaping the field and categorize these works under three broad umbrellas: (i) those grounded in Western canonical philosophy, (ii) mathematical and statistical methods, and (iii) those emerging from critical data/algorithm/information studies. We also survey the field and explore emerging trends by examining the rapidly growing body of literature that falls under the broad umbrella of AI Ethics. To that end, we read and annotated peer-reviewed papers published over the past four years in two premier conferences: FAccT and AIES. We organize the literature based on an annotation scheme we developed according to three main dimensions: whether the paper deals with concrete applications, use-cases, and/or people's lived experience; to what extent it addresses harmed, threatened, or otherwise marginalized groups; and if so, whether it explicitly names such groups. We note that although the goals of the majority of FAccT and AIES papers were often commendable, their consideration of the negative impacts of AI on traditionally marginalized groups remained shallow. Taken together, our conceptual analysis and the data from annotated papers indicate that the field would benefit from an increased focus on ethical analysis grounded in concrete use-cases, people's experiences, and applications as well as from approaches that are sensitive to structural and historical power asymmetries.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

The Transformer Network for the Traveling Salesman Problem

The Traveling Salesman Problem (TSP) is the most popular and most studied combinatorial problem, starting with von Neumann in 1951. It has driven the discovery of several optimization techniques such as cutting planes, branch-and-bound, local search, Lagrangian relaxation, and simulated annealing. The last five years have seen the emergence of promising techniques where (graph) neural networks have been capable to learn new combinatorial algorithms. The main question is whether deep learning can learn better heuristics from data, i.e. replacing human-engineered heuristics? This is appealing because developing algorithms to tackle efficiently NP-hard problems may require years of research, and many industry problems are combinatorial by nature. In this work, we propose to adapt the recent successful Transformer architecture originally developed for natural language processing to the combinatorial TSP. Training is done by reinforcement learning, hence without TSP training solutions, and decoding uses beam search. We report improved performances over recent learned heuristics with an optimal gap of 0.004% for TSP50 and 0.39% for TSP100.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

A Mutation-based Approach for Assessing Weight Coverage of a Path Planner

Autonomous cars are subjected to several different kind of inputs (other cars, road structure, etc.) and, therefore, testing the car under all possible conditions is impossible. To tackle this problem, scenario-based testing for automated driving defines categories of different scenarios that should be covered. Although this kind of coverage is a necessary condition, it still does not guarantee that any possible behaviour of the autonomous car is tested. In this paper, we consider the path planner of an autonomous car that decides, at each timestep, the short-term path to follow in the next few seconds; such decision is done by using a weighted cost function that considers different aspects (safety, comfort, etc.). In order to assess whether all the possible decisions that can be taken by the path planner are covered by a given test suite T, we propose a mutation-based approach that mutates the weights of the cost function and then checks if at least one scenario of T kills the mutant. Preliminary experiments on a manually designed test suite show that some weights are easier to cover as they consider aspects that more likely occur in a scenario, and that more complicated scenarios (that generate more complex paths) are those that allow to cover more weights.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A recurrent neural network without chaos

We introduce an exceptionally simple gated recurrent neural network (RNN) that achieves performance comparable to well-known gated architectures, such as LSTMs and GRUs, on the word-level language modeling task. We prove that our model has simple, predicable and non-chaotic dynamics. This stands in stark contrast to more standard gated architectures, whose underlying dynamical systems exhibit chaotic behavior.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Assessing and Improving the Mutation Testing Practice of PIT

Mutation testing is used extensively to support the experimentation of software engineering studies. Its application to real-world projects is possible thanks to modern tools that automate the whole mutation analysis process. However, popular mutation testing tools use a restrictive set of mutants which do not conform to the community standards as supported by the mutation testing literature. This can be problematic since the effectiveness of mutation depends on its mutants. We therefore examine how effective are the mutants of a popular mutation testing tool, named PIT, compared to comprehensive ones, as drawn from the literature and personal experience. We show that comprehensive mutants are harder to kill and encode faults not captured by the mutants of PIT for a range of 11% to 62% of the Java classes of the considered projects.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

The regularity of the boundary of a multidimensional aggregation patch

Let $d \geq 2$ and let $N(y)$ be the fundamental solution of the Laplace equation in $R^d$ We consider the aggregation equation $$ \frac{\partial ρ}{\partial t} + \operatorname{div}(ρv) =0, v = -\nabla N * ρ$$ with initial data $ρ(x,0) = χ_{D_0}$, where $χ_{D_0}$ is the indicator function of a bounded domain $D_0 \subset R^d.$ We now fix $0 < γ< 1$ and take $D_0$ to be a bounded $C^{1+γ}$ domain (a domain with smooth boundary of class $C^{1+γ}$). Then we have Theorem: If $D_0$ is a $C^{1 + γ}$ domain, then the initial value problem above has a solution given by $$ρ(x,t) = \frac{1}{1 -t} χ_{D_t}(x), \quad x \in R^d, \quad 0 \le t < 1$$ where $D_t$ is a $C^{1 + γ}$ domain for all $0 \leq t < 1$.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Enhanced Lasso Recovery on Graph

This work aims at recovering signals that are sparse on graphs. Compressed sensing offers techniques for signal recovery from a few linear measurements and graph Fourier analysis provides a signal representation on graph. In this paper, we leverage these two frameworks to introduce a new Lasso recovery algorithm on graphs. More precisely, we present a non-convex, non-smooth algorithm that outperforms the standard convex Lasso technique. We carry out numerical experiments on three benchmark graph datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

An Incremental Reseeding Strategy for Clustering

In this work we propose a simple and easily parallelizable algorithm for multiway graph partitioning. The algorithm alternates between three basic components: diffusing seed vertices over the graph, thresholding the diffused seeds, and then randomly reseeding the thresholded clusters. We demonstrate experimentally that the proper combination of these ingredients leads to an algorithm that achieves state-of-the-art performance in terms of cluster purity on standard benchmarks datasets. Moreover, the algorithm runs an order of magnitude faster than the other algorithms that achieve comparable results in terms of accuracy. We also describe a coarsen, cluster and refine approach similar to GRACLUS and METIS that removes an additional order of magnitude from the runtime of our algorithm while still maintaining competitive accuracy.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Consistency of Cheeger and Ratio Graph Cuts

This paper establishes the consistency of a family of graph-cut-based algorithms for clustering of data clouds. We consider point clouds obtained as samples of a ground-truth measure. We investigate approaches to clustering based on minimizing objective functionals defined on proximity graphs of the given sample. Our focus is on functionals based on graph cuts like the Cheeger and ratio cuts. We show that minimizers of the these cuts converge as the sample size increases to a minimizer of a corresponding continuum cut (which partitions the ground truth measure). Moreover, we obtain sharp conditions on how the connectivity radius can be scaled with respect to the number of sample points for the consistency to hold. We provide results for two-way and for multiway cuts. Furthermore we provide numerical experiments that illustrate the results and explore the optimality of scaling in dimension two.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

A Method Based on Total Variation for Network Modularity Optimization using the MBO Scheme

The study of network structure is pervasive in sociology, biology, computer science, and many other disciplines. One of the most important areas of network science is the algorithmic detection of cohesive groups of nodes called "communities". One popular approach to find communities is to maximize a quality function known as {\em modularity} to achieve some sort of optimal clustering of nodes. In this paper, we interpret the modularity function from a novel perspective: we reformulate modularity optimization as a minimization problem of an energy functional that consists of a total variation term and an $\ell_2$ balance term. By employing numerical techniques from image processing and $\ell_1$ compressive sensing -- such as convex splitting and the Merriman-Bence-Osher (MBO) scheme -- we develop a variational algorithm for the minimization problem. We present our computational results using both synthetic benchmark networks and real data.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

An Adaptive Total Variation Algorithm for Computing the Balanced Cut of a Graph

We propose an adaptive version of the total variation algorithm proposed in [3] for computing the balanced cut of a graph. The algorithm from [3] used a sequence of inner total variation minimizations to guarantee descent of the balanced cut energy as well as convergence of the algorithm. In practice the total variation minimization step is never solved exactly. Instead, an accuracy parameter is specified and the total variation minimization terminates once this level of accuracy is reached. The choice of this parameter can vastly impact both the computational time of the overall algorithm as well as the accuracy of the result. Moreover, since the total variation minimization step is not solved exactly, the algorithm is not guarantied to be monotonic. In the present work we introduce a new adaptive stopping condition for the total variation minimization that guarantees monotonicity. This results in an algorithm that is actually monotonic in practice and is also significantly faster than previous, non-adaptive algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Multiclass Total Variation Clustering

Ideas from the image processing literature have recently motivated a new set of clustering algorithms that rely on the concept of total variation. While these algorithms perform well for bi-partitioning tasks, their recursive extensions yield unimpressive results for multiclass clustering tasks. This paper presents a general framework for multiclass total variation clustering that does not rely on recursion. The results greatly outperform previous total variation algorithms and compare well with state-of-the-art NMF approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Characterization of radially symmetric finite time blowup in multidimensional aggregation equations,

This paper studies the transport of a mass $μ$ in $\real^d, d \geq 2,$ by a flow field $v= -\nabla K*μ$. We focus on kernels $K=|x|^α/ α$ for $2-d\leq α<2$ for which the smooth densities are known to develop singularities in finite time. For this range This paper studies the transport of a mass $μ$ in $\real^d, d \geq 2,$ by a flow field $v= -\nabla K*μ$. We focus on kernels $K=|x|^α/ α$ for $2-d\leq α<2$ for which the smooth densities are known to develop singularities in finite time. For this range we prove the existence for all time of radially symmetric measure solutions that are monotone decreasing as a function of the radius, thus allowing for continuation of the solution past the blowup time. The monotone constraint on the data is consistent with the typical blowup profiles observed in recent numerical studies of these singularities. We prove monotonicity is preserved for all time, even after blowup, in contrast to the case $α>2$ where radially symmetric solutions are known to lose monotonicity. In the case of the Newtonian potential ($α=2-d$), under the assumption of radial symmetry the equation can be transformed into the inviscid Burgers equation on a half line. This enables us to prove preservation of monotonicity using the classical theory of conservation laws. In the case $2 -d < α< 2$ and at the critical exponent $p$ we exhibit initial data in $L^p$ for which the solution immediately develops a Dirac mass singularity. This extends recent work on the local ill-posedness of solutions at the critical exponent.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Convergence of a Steepest Descent Algorithm for Ratio Cut Clustering

Unsupervised clustering of scattered, noisy and high-dimensional data points is an important and difficult problem. Tight continuous relaxations of balanced cut problems have recently been shown to provide excellent clustering results. In this paper, we present an explicit-implicit gradient flow scheme for the relaxed ratio cut problem, and prove that the algorithm converges to a critical point of the energy. We also show the efficiency of the proposed algorithm on the two moons dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

The Planar Optics Phase Sensor: a study for the VLTI 2nd Generation Fringe Tracker

In a few years, the second generation instruments of the Very Large Telescope Interferometer (VLTI) will routinely provide observations with 4 to 6 telescopes simultaneously. To reach their ultimate performance, they will need a fringe sensor capable to measure in real time the randomly varying optical paths differences. A collaboration between LAOG (PI institute), IAGL, OCA and GIPSA-Lab has proposed the Planar Optics Phase Sensor concept to ESO for the 2nd Generation Fringe Tracker. This concept is based on the integrated optics technologies, enabling the conception of extremely compact interferometric instruments naturally providing single-mode spatial filtering. It allows operations with 4 and 6 telescopes by measuring the fringes position thanks to a spectrally dispersed ABCD method. We present here the main analysis which led to the current concept as well as the expected on-sky performance and the proposed design.

0 citations0 reviewsNo code linkedOpen access