Publications

D-CLIPSE: Distributed Consensus-based Localization with Passive Listening on Shared State Exchange
Kyle Biron-Gricken
James Richard Forbes
Multi-robot localization that is accurate and consistent is imperative for downstream tasks such as planning and control. Centralized filter… (see more)ing approaches optimally fuse all available sensor measurements of the team. However, a centralized solution is rarely implementable due to hardware, communication, and computational constraints. Distributed approaches deploy a filter on each robot to estimate their own state and neighbours' states using inter-robot communication. This paper proposes a consistent, communication-efficient, and consensus-based distributed filtering framework that shares both preintegrated odometry and relevant shared states among communicating robots. The proposed method is validated in simulated and experimental scenarios, showing near centralized performance in accuracy, and especially in consistency, compared to the current state-of-the-art decentralized approach.
2026-07-08
arXiv (preprint)
doi.org
arxiv.org
Parallel versions of the mesh adaptive direct search algorithm
Sébastien Le Digabel
Antoine Lesage-Landry
Samuel Mendoza
Christophe Tribes
This work surveys the different parallel variants of the mesh adaptive direct search (MADS) algorithm for constrained blackbox optimization.… (see more) These problems can inherently imply high computational costs due to the possible large number of variables and multi-modality of the search space. In addition, the potential time-intensive nature and time heterogeneity of the blackboxes defining the problem prompts the need for efficient implementations. Parallelism emerges as an actionable solution to mitigate computation time, as modern computer systems rely on multi-core architecture. The reviewed methods employ diverse levels of parallelism and distinct parallel strategies to effectively tackle each aspect outlined above. The manuscript details the practical implementations, provides computational results, and offers insights into the advantages and limitations of each MADS parallel method.
2026-07-08
arXiv (preprint)
doi.org
arxiv.org
SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions
Elham Daneshmand
Majid Khadiv
Glen Berseth
Hsiu-Chin Lin
Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot … (see more)be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do. A standard mitigation hands control to a separate recovery policy whenever the agent leaves a designer-specified safe region (a subset of state space it should stay within), but the resulting mixed-policy rollouts silently bias every on-policy update, and the importance-sampling correction that would remove this bias is ill-defined whenever the recovery policy is deterministic. We address this bias with a drop-in modification of proximal policy optimization (PPO). Its core is an unbiased policy-gradient estimator that uses the score function only at safe timesteps and never evaluates the recovery policy's density, so it stays valid even when the recovery policy is deterministic, exactly where importance sampling breaks, and it empirically dominates importance sampling even when the recovery policy is stochastic. Because the recovery policy still makes credit assignment slow near the safe-region boundary, two further components accelerate learning: a closed-form value for recovery-triggering states when dynamics and recovery are deterministic, and an imitation loss that copies recovery actions only when recovery succeeds. On a three-environment, five-seed benchmark, the resulting algorithm reduces training-time falls by factors of 233x, 48x, and 26x on HalfCheetah, Ant, and Unitree Go1 over standard PPO, while matching or exceeding PPO's final reward, and on Ant, where the recovery policy is unreliable, it is the only method that reaches 80% of the best final reward.
2026-07-08
arXiv (preprint)
doi.org
arxiv.org
Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
Matthias Tangemann
Benjamin Lo
Zygmunt Pizlo
Kaleem Siddiqi
Dirk B. Walther
Sven Dickinson
Figure-ground organization in the human visual system relies on several shape-based cues, including surroundedness, convexity, and symmetry.… (see more) While these cues have been extensively studied using abstract stimuli, little is known about how they operate under natural conditions or how they arise from the statistics of natural scenes. Deep neural networks offer a promising path forward: a model that relies on the same figure-ground cues as humans would provide tractable experimental access to the underlying mechanisms. In this study, we evaluate shape-based figure-ground organization in Vision Transformers (ViTs), for which prior work has demonstrated the emergence of object-based grouping. We test 25 ViTs spanning supervised and self-supervised training objectives, by fitting linear probes to predict figure-ground assignment from intermediate patch representations using both natural images and controlled artificial stimuli that isolate individual cues. Our results show that ViTs robustly encode surroundedness and convexity, and that probes trained on natural images generalize zero-shot to artificial stimuli across several models. For symmetry we observe mixed results: the cue is encoded for uniformly colored but not for textured regions. Taken together, our findings demonstrate that Gestalt-like figure-ground cues can be learned from natural scene statistics and position ViTs as a compelling model system for studying the computational mechanisms of perceptual organization. Code and data is available at https://github.com/mtangemann/mlvbench
2026-07-08
arXiv (preprint)
doi.org
arxiv.org
Empirical Comparison of Unified Benders Cuts for Multi-Commodity Fixed-Charge Network Design
Eric Larsen
Jean-François Cordeau
Antonio Frangioni
Emma Frejinger
Among the many types of acceleration techniques designed to improve the performance of Benders decomposition, unified cut generation schemes… (see more) have recently attracted a keen interest. Unified cuts aim for a better balance between the generation of optimality and feasibility cuts, while also providing a way to compare the strengths of different feasibility cuts. Our goal is to assess the experimental performance of a broad selection of unified and distinct Benders cuts in the context of the multi-commodity fixed-charge network design problem (MCFNDP). We express under a common mathematical structure and notation the construction of each unified or distinct Benders cut considered. We also explain how the generic formulations of the Benders cuts can be specialized to conform to the specifications of the MCFNDP. In addition, we suggest bespoke methods for comparing the performance of several solution methods when the benchmark is made up of heterogeneous problem instances. We report the results of a systematic empirical analysis comparing the performances of 50 Benders methods involving unified or distinct cuts in applications to a common testing bench made up of standardized MCFNDP instances. The analysis identifies a small number of leading Benders methods, namely those featuring the static Brandenberg-Stursberg cuts and the Hosseini-Turner l1-deepest cuts. In addition, we also report results obtained by using both Gurobi and CPLEX as the supporting solver to the SMS++ computation library.
2026-07-07
arXiv (preprint)
doi.org
arxiv.org
A systematic analysis of machine learning pipelines for robust antimicrobial resistance prediction
Alex Aselstyne
Enamundram Naga Karthik
Meriem El Azami
Romain Pogorelcnik
Quentin Fournier
Sarath Chandar
Abstract Motivation Antimicrobial resistance (AMR) has been identified as a top global public health threat. Accurate AMR phenotype predicti… (see more)on from whole-genome sequencing data is an essential tool for accelerating clinical decision-making and mitigating resistance spread. Although many previous works have explored the use of tree-based machine learning (ML) models to predict resistance, the field lacks a systematic evaluation of the training pipeline across a variety of pathogenic species and antibiotics. Results Using nine clinically relevant species–antibiotic combinations from the NCBI antimicrobial susceptibility testing database, we present a detailed analysis of the ML pipeline and identify key factors affecting model performance and evaluation. We begin by relabelling all isolates using current CLSI minimum inhibitory concentration breakpoints to resolve inconsistencies and increase available data, resulting in up to a 19% label swap and 56% data enlargement per species– antibiotic combination. We identify several key training parameters including k -mer length, which can increase classification F1 scores by over 20 points compared to commonly used k -values, feature matrix truncation, which can induce polynomial time reductions with limited performance reduction, and ML model class. By comparing 5-fold cross-validation with evaluation on an unseen clinical dataset, we show that random cross-validation splits—often criticized as overly optimistic—can act as a strong proxy for downstream clinical performance, yielding closer F1 scores than phylogeny-aware splits in all cases. We finally present an interpretability study which shows that over 95% of k -mers used by our models are associated with identifiable genomic features. Our results highlight the importance of feature design, evaluation protocol, and biological analysis in genomic AMR prediction, and support tree-based models as a robust and interpretable method. Availability and implementation Python code is made freely available: https://github.com/chandar-lab/amr-pred
2026-07-07
bioRxiv (preprint)
doi.org
DNA-aware evaluation and debiasing of sequence-to-function models
Doruk Cakmakci
Yue Li
MOTIVATION: Genome sequence-to-function (S2F) models are widely used to interpret base-resolution functional genomics assays. Most S2F model… (see more)s are trained and evaluated against observed counts and profile-shapes using statistical objectives and fidelity metrics. These choices are well motivated, but they are DNA-independent. At the same time, experimental measurements arise from DNA-dependent assays with distinct characteristics. This mismatch motivates a complementary DNA-aware evaluation of S2F-predicted and experimental functional genomic tracks. RESULTS: We study DNA-dependency of experimental and S2F-predicted tracks using track-conditional genome language models (cgLMs). cgLMs predict masked nucleotides from a conditioning track under controlled DNA visibility. Across ATAC-seq and TF ChIP-seq peaks from GM12878 and K562, cgLM-probing reveals a consistent masked DNA-decodability gap between many experimental and S2F-predicted tracks. In particular, single-task (e.g. BPNet) and multi-task (e.g. AlphaGenome) S2F-predicted tracks enabled cgLMs to recover masked nucleotides with significantly higher accuracy and confidence than matched experimental tracks. Analyses of nonpeak and dinucleotide-shuffled sequences show that this gap is not confined to peaks and is not captured by standard DNA-agnostic profile-shape fidelity metrics alone. ChromBPNet Tn5-denoised predictions were an exception and behaved closer to the experimental regime, suggesting that staged training may reduce the gap. We then convert this diagnostic into a critic-derived objective, DNA-dependency matching (DDM), using a frozen multi-headed cgLM critic. We introduce Critic-Guided Profile-Shape Editing (CGPSE), a preliminary post hoc debiasing framework for frozen S2F models. In GM12878 ATAC-seq, CGPSE partially reduces the masked DNA-decodability gap for AlphaGenome and BPNet predictions, while exposing a tradeoff with profile-shape fidelity. AVAILABILITY AND IMPLEMENTATION: https://github.com/li-lab-mcgill/dna-aware-s2f-eval.
2026-07-06
Bioinformatics (published)
doi.org
Efficient Long-Horizon Learning for Learned Optimization
Xiaolong Huang
Benjamin Therien
James Harrison
Eugene Belilovsky
Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers ov… (see more)er a distribution of tasks. While recent work has greatly advanced the architectural design and inductive biases of learned optimizers (LOs), current meta-training approaches still suffer from two main difficulties: (1) they cannot efficiently scale meta-training to long-horizon inner problems and (2) they often fail to compete with strong hand-designed optimizers. To address these limitations, we propose Efficient Long-hOrizon (ELO) learning, an efficient meta-training algorithm that (1) reallocates redundant meta-training compute to longer failure regimes, achieving efficient long-horizon learning, and (2) enforces decoupled progressive expert supervision, providing stable meta-learning signals that additionally improve the generalization of LOs. Our empirical study evaluates ELO for meta-training both element-wise and matrix-based LOs. Across downstream language modeling (GPT-2-124M/350M on FineWeb) and image classification (ViT-B/16, ResNet-50 on ImageNet-1K) tasks, ELO substantially improves the long-unroll performance and out-of-distribution generalization of the base LOs. In particular, ELO-Celo2 consistently outperforms well-tuned AdamW across all evaluated tasks, while remaining competitive with Muon on language modeling. \textit{Notably, all ELO baselines require less than 7 H100 GPU-hours for meta-training.}
2026-07-06
arXiv (preprint)
doi.org
arxiv.org
Memory of Some Plants and Special Medications
Nonvikan Karl-Augustt Alahassa
Bidossessi R.U. Alahassa
Suljo Linic
Bruno Rémillard
Marlène Frigon
Mylène Bédard
Nathalie Lacelle
Élise Vandomme
Bakary Manga
J. Tossa
Maciej Augustyniak
Dimitrios Koukoulopoulos
Leonard Wantchekon
David Haziza
Samuel Bassetto
Foutse Khomh
Christiane Rousseau
Damien Échevin
Daniel F. Nadeau
Emmanuel Stip … (see 6 more)
Julie Carrier
Jérôme Théau
Raphael R. Kelani
Wilfrid Gangbo
Cyriaque Atindogbé
J. B. Chabi Orou
We have Memory of Some Plants and Special Medications. We have introduced few notes about.
2026-07-06
Zenodo (unknown)
doi.org
DIVO: Continuous-time DVL-Inertial-Visual Odometry for Unmanned Underwater Vehicles
Kyungmin Jung
Angad Bajwa
Junha Yoo
Arturo Del Castillo Bernal
James Richard Forbes
This paper presents a novel acoustic-visual-inertial odometry solution leveraging a continuous-time trajectory estimation framework for unma… (see more)nned underwater vehicles. Underwater environments present unique challenges for visual localization and mapping, such as light attenuation, illumination variance, and the presence of particulate matter. This motivates the use of additional sensing modalities and a visual tracking pipeline that is robust to diverse subsea conditions. The proposed system is the first continuous-time trajectory estimation framework based on Gaussian processes to fuse asynchronous measurements from a Doppler velocity log, a stereo camera, and an inertial measurement unit. Additionally, a novel visual frontend is proposed, incorporating learning-based feature extraction and matching that is robust to the specific challenges that subsea environments present. The proposed framework enables seamless integration of additional sensor modalities in continuous-time and is adaptable to different environments without reconfiguration. The proposed system is extensively tested on real-world underwater inspection datasets, where it outperforms state-of-the-art visual-inertial and acoustic-visual-inertial SLAM algorithms in accuracy, robustness, and trajectory coverage. Notably, the proposed system outperforms the state-of-the-art despite only forming short-term visual data associations.
2026-07-05
arXiv (preprint)
doi.org
arxiv.org
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
Mohamed Amine Merzouk
Dmitri Carpov
Mirko Bronzi
Damiano Fornasiere
Adam Oberman
Large language models generate one token at a time, yet their responses show remarkably consistent length structure: step-by-step solutions … (see more)converge in predictable token counts, retrievals stop after a few sentences, retractions extend responses by measurable amounts. We ask whether the model carries an internal estimate of how much response remains. Training minimal-capacity linear probes on frozen hidden states of three open-weight 7-8B models across seven completion-style datasets, we find three converging pieces of evidence. First, total response length is linearly decodable from the prompt's last hidden state alone, before any output is emitted. Second, probe directions trained on natural-language datasets transfer broadly, including to controlled synthetic completions never seen in training, outperforming a statistical baseline; the converse direction generally fails, and this asymmetry is itself informative. Third, on curated high-loss completions, the probe's per-position estimate shifts upward at the moment the model retracts and restarts a partial solution, a directional behavior no position-only predictor can reproduce (qualitative, not aggregate). We frame this as approximate estimation of remaining generation length, distinct from exact-counting impossibility results for transformers, and interpret it as evidence that LLMs maintain a plan-like internal representation of output length (decodable, not necessarily used causally).
2026-07-05
arXiv (preprint)
doi.org
arxiv.org
PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
Shubham Gupta
Nazanin Mohammadi Sepahvand
Abhinav Kumar
Cem Subakan
Spandana Gella
Pierre-Andre Noel
Perouz Taslakian
Eugene Bagdasarian
Valentina Zantedeschi
As LLM agents evolve from single-user assistants into shared organizational infrastructure, new privacy risks emerge: inappropriate informat… (see more)ion may not only be exposed through outputs for external recipients, but also internally across users through inter-agent messages, shared memory and agents. These data spillage risks are not captured by existing privacy benchmarks grounded in contextual integrity (CI) as they focus primarily on either single-user settings or interactions between independently owned agents. We introducePiSAs (Privacy in Shared Agentic systems), a benchmark for assessing unintentional leaks with dual CI annotations: whether an information is appropriate for the task, and which users may legitimately access it. This enables direct measurement of cross-user spillage across agentic system components and interfaces, such as outputs, inter-agent communication, and memory. PiSAsis system-agnostic and supports evaluation across different agent topologies and memory regimes. We find that, although system design improves CI compliance, results are bottlenecked by incorrect LLM judgment calls: even state-of-the-art models fail to reliably filter inappropriate content or restrict transmission to authorized users. Our findings underscore the need for privacy-preserving strategies, beyond those studied in this work.
2026-07-05
arXiv (preprint)
doi.org
arxiv.org