Wearable accelerometers are used for a wide range of applications, such as gesture recognition, gait analysis, and sports monitoring. Y et most existing foundation models focus primarily on classifying common daily activities such as locomotion and exercise, limiting their applicability to the broader range of tasks that rely on other signal characteristics. SlotFM uses Time-Frequency Slot Attention, an extension of Slot Attention that processes both time and frequency representations of the raw signals. It generates multiple small embeddings (slots), each capturing different signal components, enabling task-specific heads to focus on the most relevant parts of the data. We also introduce two loss regularizers that capture local structure and frequency patterns, which improve reconstruction of fine-grained details and helps the embeddings preserve task-relevant information. We evaluate SlotFM on 16 classification and regression downstream tasks that extend beyond standard human activity recognition. It outperforms existing self-supervised approaches on 13 of these tasks and achieves comparable results to the best performing approaches on the remaining tasks. On average, our method yields a 4.5% performance gain, demonstrating strong generalization for sensing foundation models. Advances in self-supervised learning (SSL) and large-scale datasets have enabled foundation models that support multiple tasks through shared representations (Y ang et al., 2024; Oquab et al., 2023). This is particularly valuable for wearable devices, where maintaining separate models dedicated for each task is often impractical due to memory and compute constraints. Accelerometers are widely used sensors in wearables for diverse motion-related tasks. Recent studies show that SSL approaches can train foundation models effective in Human Activity Recognition (HAR) tasks such as exercise and locomotion classification (Logacjov, 2024). However, their applicability to broader accelerometer tasks, such as gait analysis and gesture recognition, remains largely unexplored. This contrasts with domains such as audio, where foundation models have been applied beyond a single task, spanning speech-to-text, speaker identification, and emotion recognition.

Abstract--We study whether 3D self-supervised pretraining with Point-JEPA enables label-efficient grasp joint-angle prediction. Meshes are sampled to point clouds and tokenized; a ShapeNet-pretrained Point-JEPA encoder feeds a K=5 multi-hypothesis head trained with winner-takes-all and evaluated by top-logit selection. On a multi-finger hand dataset with strict object-level splits, Point-JEPA improves top-logit RMSE and Coverage@15 in low-label regimes (e.g., 26% lower RMSE at 25% data) and reaches parity at full supervision, suggesting JEPA-style pretraining is a practical lever for data-efficient grasp learning. Self-supervised learning (SSL) for 3D data has largely progressed along three directions. On point clouds this includes point/voxel masked autoencoding; e.g., V oxel-MAE reconstructs masked voxels for sparse automotive LiDAR and improves downstream tasks with fewer labels [1]-[4].

Money laundering enables organized crime by moving illicit funds into the legitimate economy. Although trillions of dollars are laundered each year, detection rates remain low because launderers evade oversight, confirmed cases are rare, and institutions see only fragments of the global transaction network. Since access to real transaction data is tightly restricted, synthetic datasets are essential for developing and evaluating detection methods. However, existing datasets fall short: they often neglect partial observability, temporal dynamics, strategic behavior, uncertain labels, class imbalance, and network-level dependencies. We introduce AMLGentex, an open-source suite for generating realistic, configurable transaction data and benchmarking detection methods. AMLGentex enables systematic evaluation of anti-money laundering systems under conditions that mirror real-world challenges. By releasing multiple country-specific datasets and practical parameter guidance, we aim to empower researchers and practitioners and provide a common foundation for collaboration and progress in combating money laundering.

Linking implicit scientific claims made on social media to their original publications is crucial for evidence-based fact-checking and scholarly discourse, yet it is hindered by lexical sparsity, very short queries, and domain-specific language. Team AIRwaves ranked second in Subtask 4b of the CLEF-2025 CheckThat! Lab with an evidence-retrieval approach that markedly outperforms the competition baseline. The optimized sparse-retrieval baseline(BM25) achieves MRR@5 = 0.5025 on the gold label blind test set. To surpass this baseline, a two-stage retrieval pipeline is introduced: (i) a first stage that uses a dual encoder based on E5-large, fine-tuned using in-batch and mined hard negatives and enhanced through chunked tokenization and rich document metadata; and (ii) a neural re-ranking stage using a SciBERT cross-encoder. Replacing purely lexical matching with neural representations lifts performance to MRR@5 = 0.6174, and the complete pipeline further improves to MRR@5 = 0.6828. The findings demonstrate that coupling dense retrieval with neural re-rankers delivers a powerful and efficient solution for tweet-to-study matching and provides a practical blueprint for future evidence-retrieval pipelines.

Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited supervision, we propose Self-Evolved Imitation Learning (SEIL), a framework that progressively improves a few-shot model through simulator interactions. The model first attempts tasksin the simulator, from which successful trajectories are collected as new demonstrations for iterative refinement. To enhance the diversity of these demonstrations, SEIL employs dual-level augmentation: (i) Model-level, using an Exponential Moving Average (EMA) model to collaborate with the primary model, and (ii) Environment-level, introducing slight variations in initial object positions. We further introduce a lightweight selector that filters complementary and informative trajectories from the generated pool to ensure demonstration quality. These curated samples enable the model to achieve competitive performance with far fewer training examples. Extensive experiments on the LIBERO benchmark show that SEIL achieves a new state-of-the-art performance in few-shot imitation learning scenarios. Code is available at https://github.com/Jasper-aaa/SEIL.git.

Hyperspectral imaging (HSI) provides rich spectral information for medical imaging, yet encounters significant challenges due to data limitations and hardware variations. We introduce SAMSA, a novel interactive segmentation framework that combines an RGB foundation model with spectral analysis. SAMSA efficiently utilizes user clicks to guide both RGB segmentation and spectral similarity computations. The method addresses key limitations in HSI segmentation through a unique spectral feature fusion strategy that operates independently of spectral band count and resolution. Performance evaluation on publicly available datasets has shown 81.0% 1-click and 93.4% 5-click DICE on a neurosurgical and 81.1% 1-click and 89.2% 5-click DICE on an intraoperative porcine hyperspectral dataset. Experimental results demonstrate SAMSA's effectiveness in few-shot and zero-shot learning scenarios and using minimal training examples. Our approach enables seamless integration of datasets with different spectral characteristics, providing a flexible framework for hyperspectral medical image analysis.

In practical machine learning applications, it is often challenging to assign accurate labels to data, and increasing the number of labeled instances is often limited. In such cases, Weakly Supervised Learning (WSL), which enables training with incomplete or imprecise supervision, provides a practical and effective solution. However, most existing WSL methods focus on leveraging a single type of weak supervision. In this paper, we propose a novel WSL framework that leverages complementary weak supervision signals from multiple relational perspectives, which can be especially valuable when labeled data is limited. Specifically, we introduce SconfConfDiff Classification, a method that integrates two distinct forms of weaklabels: similarity-confidence and confidence-difference, which are assigned to unlabeled data pairs. To implement this method, we derive two types of unbiased risk estimators for classification: one based on a convex combination of existing estimators, and another newly designed by modeling the interaction between two weak labels. We prove that both estimators achieve optimal convergence rates with respect to estimation error bounds. Furthermore, we introduce a risk correction approach to mitigate overfitting caused by negative empirical risk, and provide theoretical analysis on the robustness of the proposed method against inaccurate class prior probability and label noise. Experimental results demonstrate that the proposed method consistently outperforms existing baselines across a variety of settings.

Combining multimodal data is a key issue in a wide range of machine learning tasks, including many remote sensing problems. In Earth observation, early multimodal data fusion methods were based on specific neural network architectures and supervised learning. Ever since, the scarcity of labeled data has motivated self-supervised learning techniques. State-of-the-art multimodal representation learning techniques leverage the spatial alignment between satellite data from different modalities acquired over the same geographic area in order to foster a semantic alignment in the latent space. In this paper, we investigate how this methods can preserve task-relevant information that is not shared across modalities. First, we show, under simplifying assumptions, when alignment strategies fundamentally lead to an information loss. Then, we support our theoretical insight through numerical experiments in more realistic settings. With those theoretical and empirical evidences, we hope to support new developments in contrastive learning for the combination of multimodal satellite data. Our code and data is publicly available at https://github.com/Romain3Ch216/alg_maclean_25.

ABSTRACT Self-supervised learning (SSL) has made significant advances in speech representation learning. Models like wav2vec 2.0 and HuBERT have achieved state-of-the-art results in tasks such as speech recognition, particularly in monolingual settings. However, multilingual SSL models tend to underperform their monolingual counterparts on each individual language, especially in multilingual scenarios with few languages such as the bilingual setting. In this work, we investigate a novel approach to reduce this performance gap by introducing limited visual grounding into bilingual speech SSL models. Our results show that visual grounding benefits both monolingual and bilingual models, with especially pronounced gains for the latter, reducing the multilingual performance gap on zero-shot phonetic discrimination from 31.5% for audio-only models to 8.04% with grounding.

The development of multimodal models for pulmonary nodule diagnosis is limited by the scarcity of labeled data and the tendency for these models to overfit on the training distribution. In this work, we leverage self-supervised learning from longitudinal and multimodal archives to address these challenges. We curate an unlabeled set of patients with CT scans and linked electronic health records from our home institution to power joint embedding predictive architecture (JEPA) pretraining. After supervised finetuning, we show that our approach outperforms an unregularized multimodal model and imaging-only model in an internal cohort (ours: 0.91, multimodal: 0.88, imaging-only: 0.73 AUC), but underperforms in an external cohort (ours: 0.72, imaging-only: 0.75 AUC). We develop a synthetic environment that characterizes the context in which JEPA may underperform. This work innovates an approach that leverages unlabeled multimodal medical archives to improve predictive models and demonstrates its advantages and limitations in pulmonary nodule diagnosis.