David Rousseau

Biwei Dai, Po-Wen Chang, Wahid Bhimji et al.

Weak gravitational lensing, the correlated distortion of background galaxy shapes by foreground structures, is a powerful probe of the matter distribution in our universe and allows accurate constraints on the cosmological model. In recent years, high-order statistics and machine learning (ML) techniques have been applied to weak lensing data to extract the nonlinear information beyond traditional two-point analysis. However, these methods typically rely on cosmological simulations, which poses several challenges: simulations are computationally expensive, limiting most realistic setups to a low training data regime; inaccurate modeling of systematics in the simulations create distribution shifts that can bias cosmological parameter constraints; and varying simulation setups across studies make method comparison difficult. To address these difficulties, we present the first weak lensing benchmark dataset with several realistic systematics and launch the FAIR Universe Weak Lensing Machine Learning Uncertainty Challenge. The challenge focuses on measuring the fundamental properties of the universe from weak lensing data with limited training set and potential distribution shifts, while providing a standardized benchmark for rigorous comparison across methods. Organized in two phases, the challenge will bring together the physics and ML communities to advance the methodologies for handling systematic uncertainties, data efficiency, and distribution shifts in weak lensing analysis with ML, ultimately facilitating the deployment of ML approaches into upcoming weak lensing survey analysis.

Nima Hatami, Tae-Hee Cho, Laura Mechtouff et al.

Clinical outcome prediction plays an important role in stroke patient management. From a machine learning point-of-view, one of the main challenges is dealing with heterogeneous data at patient admission, i.e. the image data which are multidimensional and the clinical data which are scalars. In this paper, a multimodal convolutional neural network - long short-term memory (CNN-LSTM) based ensemble model is proposed. For each MR image module, a dedicated network provides preliminary prediction of the clinical outcome using the modified Rankin scale (mRS). The final mRS score is obtained by merging the preliminary probabilities of each module dedicated to a specific type of MR image weighted by the clinical metadata, here age or the National Institutes of Health Stroke Scale (NIHSS). The experimental results demonstrate that the proposed model surpasses the baselines and offers an original way to automatically encode the spatio-temporal context of MR images in a deep learning architecture. The highest AUC (0.77) was achieved for the proposed model with NIHSS.

Stephen G. Dale, Nikita Kazeev, Alastair J. A. Price et al.

Artificial intelligence and machine learning are reshaping how we approach scientific discovery, not by replacing established methods but by extending what researchers can probe, predict, and design. In this roadmap we provide a forward-looking view of AI-enabled science across biology, chemistry, climate science, mathematics, materials science, physics, self-driving laboratories and unconventional computing. Several shared themes emerge: the need for diverse and trustworthy data, transferable electronic-structure and interatomic models, AI systems integrated into end-to-end scientific workflows that connect simulations to experiments and generative systems grounded in synthesisability rather than purely idealised phases. Across domains, we highlight how large foundation models, active learning and self-driving laboratories can close loops between prediction and validation while maintaining reproducibility and physical interpretability. Taken together, these perspectives outline where AI-enabled science stands today, identify bottlenecks in data, methods and infrastructure, and chart concrete directions for building AI systems that are not only more powerful but also more transparent and capable of accelerating discovery in complex real-world environments.

Nima Hatami, Laura Mechtouff, David Rousseau et al.

Patient outcome prediction is critical in management of ischemic stroke. In this paper, a novel machine learning model is proposed for stroke outcome prediction using multimodal Magnetic Resonance Imaging (MRI). The proposed model consists of two serial levels of Autoencoders (AEs), where different AEs at level 1 are used for learning unimodal features from different MRI modalities and a AE at level 2 is used to combine the unimodal features into compressed multimodal features. The sequences of multimodal features of a given patient are then used by an LSTM network for predicting outcome score. The proposed AE2-LSTM model is proved to be an effective approach for better addressing the multimodality and volumetric nature of MRI data. Experimental results show that the proposed AE2-LSTM outperforms the existing state-of-the art models by achieving highest AUC=0.71 and lowest MAE=0.34.

Kerem Mertoğlu, Yusuf Şalk, Server Karahan Sarıkaya et al.

Creation of new annotated public datasets is crucial in helping advances in 3D computer vision and machine learning meet their full potential for automatic interpretation of 3D plant models. Despite the proliferation of deep neural network architectures for segmentation and phenotyping of 3D plant models in the last decade, the amount of data, and diversity in terms of species and data acquisition modalities are far from sufficient for evaluation of such tools for their generalization ability. To contribute to closing this gap, we introduce PLANesT-3D; a new annotated dataset of 3D color point clouds of plants. PLANesT-3D is composed of 34 point cloud models representing 34 real plants from three different plant species: \textit{Capsicum annuum}, \textit{Rosa kordana}, and \textit{Ribes rubrum}. Both semantic labels in terms of "leaf" and "stem", and organ instance labels were manually annotated for the full point clouds. PLANesT-3D introduces diversity to existing datasets by adding point clouds of two new species and providing 3D data acquired with the low-cost SfM/MVS technique as opposed to laser scanning or expensive setups. Point clouds reconstructed with SfM/MVS modality exhibit challenges such as missing data, variable density, and illumination variations. As an additional contribution, SP-LSCnet, a novel semantic segmentation method that is a combination of unsupervised superpoint extraction and a 3D point-based deep learning approach is introduced and evaluated on the new dataset. The advantages of SP-LSCnet over other deep learning methods are its modular structure and increased interpretability. Two existing deep neural network architectures, PointNet++ and RoseSegNet, were also tested on the point clouds of PLANesT-3D for semantic segmentation.

Lukman Ismaila, Pejman Rasti, Jean-Michel Lemée et al.

We refer to a machine learning situation where models based on classical convolutional neural networks have shown good performance. We are investigating different encoding techniques in the form of supervoxels, then graphs to reduce the complexity of the model while tracking the loss of performance. This approach is illustrated on a recognition task of resting-state functional networks for patients with brain tumors. Graphs encoding supervoxels preserve activation characteristics of functional brain networks from images, optimize model parameters by 26 times while maintaining CNN model performance.

Simon Ravé, Pejman Rasti, David Rousseau

Decreasing sequence length is a common way to accelerate transformers, but prior token reduction work often targets classification and reports proxy metrics rather than end-to-end latency. For semantic segmentation, token reduction is further constrained by the need to reconstruct dense, pixel-aligned features, and on modern accelerators the overhead of computing merge maps can erase expected gains. We propose Mutual Pair Merging (MPM), a training-free token aggregation module that forms mutual nearest-neighbor pairs in cosine space, averages each pair, and records a merge map enabling a gather-based reconstruction before the decoder so that existing segmentation heads can be used unchanged. MPM introduces no learned parameters and no continuous compression knob (no keep-rate or threshold). The speed-accuracy trade-off is set by a discrete insertion schedule. We benchmark end-to-end latency on an NVIDIA H100 GPU (with and without FlashAttention-2) and a Raspberry Pi 5 across standard segmentation datasets. On ADE20K, MPM reduces per-image latency by up to 60% for ViT-Tiny on Raspberry Pi 5, and increases throughput by up to 20% on H100 with FlashAttention-2 while keeping the mIoU drop below 3%. These results suggest that simple, reconstruction-aware, training-free token merging can translate into practical wall-clock gains for segmentation when overhead is explicitly accounted for.

Simon Ravé, Jean-Christophe Lombardo, Pejman Rasti et al.

We present a zero-shot segmentation approach for agricultural imagery that leverages Plantnet, a large-scale plant classification model, in conjunction with its DinoV2 backbone and the Segment Anything Model (SAM). Rather than collecting and annotating new datasets, our method exploits Plantnet's specialized plant representations to identify plant regions and produce coarse segmentation masks. These masks are then refined by SAM to yield detailed segmentations. We evaluate on four publicly available datasets of various complexity in terms of contrast including some where the limited size of the training data and complex field conditions often hinder purely supervised methods. Our results show consistent performance gains when using Plantnet-fine-tuned DinoV2 over the base DinoV2 model, as measured by the Jaccard Index (IoU). These findings highlight the potential of combining foundation models with specialized plant-centric models to alleviate the annotation bottleneck and enable effective segmentation in diverse agricultural scenarios.

Lauren Anderson, Lucas Chatelain, Nicolas Tremblay et al.

The mechanosensory system of teeth is currently believed to partly rely on Odontoblast cells stimulation by fluid flow through a porosity network extending through dentin. Visualizing the smallest sub-microscopic porosity vessels therefore requires the highest achievable resolution from confocal fluorescence microscopy, the current gold standard. This considerably limits the extent of the field of view to very small sample regions. To overcome this limitation, we tested different deep learning (DL) super-resolution (SR) models to allow faster experimental acquisitions of lower resolution images and restore optimal image quality by post-processing. Three supervised 2D SR models (RCAN, pix2pix, FSRCNN) and one unsupervised (CycleGAN) were applied to a unique set of experimentally paired high- and low-resolution confocal images acquired with different sampling schemes, resulting in a pixel size increase of x2, x4, x8. Model performance was quantified using a broad set of similarity and distribution-based image quality assessment (IQA) metrics, which yielded inconsistent results that mostly contradicted our visual perception. This raises the question of the relevance of such generic metrics to efficiently target the specific structure of dental porosity. To resolve this conflicting information, the generated SR images were segmented taking into account the specific scales and morphology of the porosity network and analysed by comparing connected components. Additionally, the capacity of the SR models to preserve 3D porosity connectivity throughout the confocal image stacks was evaluated using graph analysis. This biology-driven assessment allowed a far better mechanistic interpretation of SR performance, highlighting differences in model sensitivity to weak intensity features and the impact of non-linearity in image generation, which explains the failure of standard IQA metrics.

Antoine Marot, David Rousseau, Zhen et al.

The conclusion of an AI challenge is not the end of its lifecycle; ensuring a long-lasting impact requires meticulous post-challenge activities. The long-lasting impact also needs to be organised. This chapter covers the various activities after the challenge is formally finished. This work identifies target audiences for post-challenge initiatives and outlines methods for collecting and organizing challenge outputs. The multiple outputs of the challenge are listed, along with the means to collect them. The central part of the chapter is a template for a typical post-challenge paper, including possible graphs and advice on how to turn the challenge into a long-lasting benchmark.

Sabrina Amrouche, Laurent Basara, Paolo Calafiura et al.

This paper reports on the second "Throughput" phase of the Tracking Machine Learning (TrackML) challenge on the Codalab platform. As in the first "Accuracy" phase, the participants had to solve a difficult experimental problem linked to tracking accurately the trajectory of particles as e.g. created at the Large Hadron Collider (LHC): given O($10^5$) points, the participants had to connect them into O($10^4$) individual groups that represent the particle trajectories which are approximated helical. While in the first phase only the accuracy mattered, the goal of this second phase was a compromise between the accuracy and the speed of inference. Both were measured on the Codalab platform where the participants had to upload their software. The best three participants had solutions with good accuracy and speed an order of magnitude faster than the state of the art when the challenge was designed. Although the core algorithms were less diverse than in the first phase, a diversity of techniques have been used and are described in this paper. The performance of the algorithms are analysed in depth and lessons derived.

Mouad Zine-El-Abidine, Helin Dutagaci, Gilles Galopin et al.

We propose a 3D color point cloud processing pipeline to count apples on individual apple trees in trellis structured orchards. Fruit counting at the tree level requires separating trees, which is challenging in dense orchards. We employ point clouds acquired from the leaf-off orchard in winter period, where the branch structure is visible, to delineate tree crowns. We localize apples in point clouds acquired in harvest period. Alignment of the two point clouds enables mapping apple locations to the delineated winter cloud and assigning each apple to its bearing tree. Our apple assignment method achieves an accuracy rate higher than 95%. In addition to presenting a first proof of feasibility, we also provide suggestions for further improvement on our apple assignment pipeline.

Kaya Turgut, Helin Dutagaci, Gilles Galopin et al.

Segmentation of structural parts of 3D models of plants is an important step for plant phenotyping, especially for monitoring architectural and morphological traits. Current state-of-the art approaches rely on hand-crafted 3D local features for modeling geometric variations in plant structures. While recent advancements in deep learning on point clouds have the potential of extracting relevant local and global characteristics, the scarcity of labeled 3D plant data impedes the exploration of this potential. We adapted six recent point-based deep learning architectures (PointNet, PointNet++, DGCNN, PointCNN, ShellNet, RIConv) for segmentation of structural parts of rosebush models. We generated 3D synthetic rosebush models to provide adequate amount of labeled data for modification and pre-training of these architectures. To evaluate their performance on real rosebush plants, we used the ROSE-X data set of fully annotated point cloud models. We provided experiments with and without the incorporation of synthetic data to demonstrate the potential of point-based deep learning techniques even with limited labeled data of real plants. The experimental results show that PointNet++ produces the highest segmentation accuracy among the six point-based deep learning methods. The advantage of PointNet++ is that it provides a flexibility in the scales of the hierarchical organization of the point cloud data. Pre-training with synthetic 3D models boosted the performance of all architectures, except for PointNet.

Kim Albertsson, Piero Altoe, Dustin Anderson et al.

Machine learning has been applied to several problems in particle physics research, beginning with applications to high-level physics analysis in the 1990s and 2000s, followed by an explosion of applications in particle and event identification and reconstruction in the 2010s. In this document we discuss promising future research and development areas for machine learning in particle physics. We detail a roadmap for their implementation, software and hardware resource requirements, collaborative initiatives with the data science community, academia and industry, and training the particle physics community in data science. The main objective of the document is to connect and motivate these areas of research and development with the physics drivers of the High-Luminosity Large Hadron Collider and future neutrino experiments and identify the resource needs for their implementation. Additionally we identify areas where collaboration with external communities will be of great benefit.