Self-Supervised Pre-Training

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 64% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 155

Oct 7, 2026cs.LG

MorphCL: Morphological Contrastive Learning for Inertial-based Human Activity Recognition

Despite the ubiquity of sensors in wearable and mobile devices and the abundance of human movement data they generate, translating unlabeled recordings into foundational motion models remains an open challenge. Self-supervised learning (SSL) has alleviated the need for costly annotations, yet existing approaches leave the global structure of large-scale motion data largely untapped, relying on randomly sampled batches and local comparisons that become particularly problematic for in-the-wild inertial data dominated by stationary, low-variance behaviors. Here we introduce Morphological Contrastive Learning (MorphCL), a self-supervised pretraining framework that uses structure-aware grouping to inject explicit modeling of global structure into inertial-based SSL approaches. Building on two well-established pillars of motion analysis, the discovery of motion primitives, or motifs, and domain-specific feature descriptors, we show that MorphCL substantially improves linear probing and finetuning results of learned encoders by up to 15 percentage points in F1-score. In a comparison with existing foundation models, we demonstrate that MorphCL-pretrained encoders match or surpass them models in linear probing performance while trained on

4600\times

less data. Qualitative analysis of the resulting embedding spaces further reveals morphologically meaningful cluster structure, with improved separation of kinematically similar activity classes.

Marius Bock, Yuwei Zhang, Juergen Gall +3

University of Bonn · University of Cambridge · Lamarr Institute for Machine Learning and Artificial Intelligence +1

Human Activity Recognition Motion Representation Learning Contrastive Learning Self-Supervised Pre-Training

Oct 6, 2026cs.CV

HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic data

Modern action recognition models rely on video transformers pretrained on massive collections of web-crawled videos, such as Kinetics-700. However, the use of such data raises ethical concerns, as subjects' consent is typically not obtained. Recent high-quality synthetic video datasets generated from motion-capture data, such as BEDLAM2.0, offer a promising ethical alternative. In this work, we investigate self-supervised pretraining of video transformers on synthetic human-motion datasets. We first show that directly applying the standard VideoMAE masking strategy leads to substantially worse performance than pretraining on Kinetics. To address this limitation, we propose a human-centric masking scheme that leverages body keypoints and person bounding box regions. Our approach encourages the model to focus on the structure and dynamics of human motion during pretraining. Experiments on NTU RGB+D and Toyota-Smarthome demonstrate that our method significantly outperforms standard VideoMAE pretraining on synthetic data, closing 49% of the gap to Kinetics pretraining on NTU RGB+D cross-view-subject without using a single real frame during pretraining. To promote the use of ethical action recognition models, we will publicly release our pretrained models.

Ricardo Pizarro, Roberto Valle, José M. Buenaposada +2

Universidad de Alcal´a, Alcal´a de Henares, Spain · Universidad Polit´ecnica de Madrid, Madrid, Spain · Universidad Rey Juan Carlos, M´ostoles, Spain

Synthetic Data Pretraining Masked Autoencoders Self-Supervised Pre-Training Video Action Recognition Video Representation Learning

Oct 5, 2026cs.LG

SpecBraM: What Should an EEG Foundation Model Predict? Masked Band-Power Prediction versus Waveform Reconstruction

Self-supervised EEG models often reconstruct masked waveforms or predict discrete codes. We study a task-aligned alternative: masked band-power prediction (MBP), which predicts fixed narrow-band log spectral energy for masked channel-time patches. This target retains rhythm power relevant to sleep staging while avoiding phase-sensitive waveform reconstruction and a learned codebook. Across three pretraining seeds, we compare band-power and waveform targets with matched backbones, pretraining data (2,388 hours), and training steps, including a 2x2 tokenizer-by-target design. On ISRUC and HMC sleep staging, MBP exceeds raw- and band-waveform reconstruction by 1.6-2.8 balanced-accuracy points with all labels and 4.7-7.3 points with 1% of labels under a strict linear probe; the target effect exceeds the tokenizer effect. Its frozen features reach 0.7916/0.7425 balanced accuracy, versus 0.7636/0.7227 for a matched rich handcrafted spectral baseline, although the gap is about one point with 1% of labels. Full fine-tuning reaches 0.8107/0.7669. The gains do not extend to every task with spectral cues, including motor imagery, depression screening, and vigilance regression. These results support choosing pretraining targets to match the physical quantities and spatial and temporal scales relevant to downstream labels.

Peng Xie, Yequan Bie, Jianda Mao +1

The Hong Kong University of Science and Technology

Electroencephalography Sleep Stage Classification Self-Supervised Pre-Training EEG Foundation Models

Oct 5, 2026cs.LG

dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra

We introduce a novel invariance for peptide tandem mass spectrometry data, unlocking self-supervised representation learning that improves de novo sequencing of peptides. This invariance exploits the physical relationship between precursor properties (mass and charge) and fragment-ion evidence, without requiring peptide sequence labels. We introduce dIon, which adapts the DINO framework with two latent prediction tasks, both recovering a clean teacher representation: one from a spectrum mixture, using the precursor as a selection query, and one from a partial spectrum with the precursor withheld. The first associates precursor information with fragment-ion evidence; the second prevents representational collapse onto that information alone. Mechanistic probes support both effects, and ablations show that the full objective performs best. Under identical end-to-end training, dIon initialization improves de novo peptide precision over training from scratch by 5.5 and 8.4 percentage points on the held-out MassIVE-KB and Kingdoms test sets, and by 2.3 and 4.8 percentage points with a larger supervised training corpus. The resulting models surpass fully supervised state-of-the-art de novo sequencing models on the diverse, multi-species Kingdoms corpus under the same greedy-decoding protocol. Without peptide labels, dIon learns strong native peptide-similarity geometry compared with other learned models; with limited peptide-supervised adaptation, it achieves the best retrieval and pair-discrimination performance across all representation benchmarks.

Alfred Nilsson, Joel Lapin, Samuel H. Payne +2

Science for Life Laboratory, KTH Royal Institute of Technology Stockholm, Sweden · Computational Mass Spectrometry, TUM School of Life Sciences Technical University of Munich, Freising, Germany · Biology Department, Brigham Young University Provo, Utah 84602, United States +1

Self-Supervised Pre-Training Mass Spectrometry Invariant Representation Learning Molecular Representation Learning

Oct 4, 2026cs.LG

Lightweight Semantic EEG Foundation Model for Frozen Cross-Disorder Transfer

Large-scale EEG foundation models have demonstrated promising transferability across neurological disorders, but often require millions of parameters and substantial computational resources. In this paper, we present the Universal Semantic EEG Foundation Model (USE-FM), a lightweight EEG foundation model that learns transferable neural representations through self-supervised signal reconstruction on the Temple University Hospital EEG Corpus (TUEG). After pretraining, the encoder is frozen and evaluated on two clinically distinct downstream tasks, abnormal EEG detection (TUAB) and epileptic seizure recognition (TUEP), using a unified frozen-transfer protocol against recent EEG foundation models, including LUNA-Base and CBraMod. With only 1.46 million parameters, approximately one-fifth the size of existing models, USE-FM achieves competitive overall performance, including strong sensitivity and F1-score on TUEP (SEN

75.00 \pm 14.14

, F1

70.37 \pm 4.01

), while maintaining competitive performance on TUAB (AUC

85.24 \pm 5.61

). Beyond downstream classification, latent representation analysis using

k

-means clustering together with PCA and t-SNE demonstrates that USE-FM learns organized semantic EEG representations comparable to substantially larger foundation models. These results suggest that large-scale self-supervised pretraining enables lightweight architectures to learn transferable semantic EEG representations, providing a computationally efficient foundation for cross-disorder analysis and future clinical decision support in neurological disorders.

Rita Huan-Ting Peng, Nhat Bui

University of Illinois Urbana–Champaign, Urbana, IL, USA · Carle Foundation Hospital, Urbana, IL, USA

EEG Seizure Detection Self-Supervised Pre-Training EEG Foundation Models

Oct 1, 2026cs.LG

Artifact Annotations Partially Substitute for Per-User Calibration: SAFE-EDA and a Normalization-Controlled Evaluation of Wrist-EDA Affect Recognition

Wrist electrodermal activity (EDA) differs in amplitude from one person to the next, so affect-recognition models normalize their input before classification. Studies that test such models on held-out subjects seldom report where the normalization statistics come from, yet statistics computed from the held-out subject's own recording give the model information that a device does not have when it is first worn. We asked how this choice alters the measured benefit of pretraining. A compact convolutional network, SAFE-EDA, was pretrained on expert artifact annotations from 43 subjects and compared with the same network trained from scratch on the Wearable Stress and Affect Detection (WESAD) dataset (15 subjects, leave-one-subject-out), with two normalization sources crossed with four window hops. When the statistics came only from training subjects, pretraining raised macro-F1 by 0.078 to 0.227; when they came from the held-out user's full recording, the gain fell to between 0.020 and 0.050 and was no longer significant. Artifact supervision was far more useful than self-supervised pretraining on the same recordings (0.078 versus 0.008). Across 13 configurations in two datasets, the pretrained network was better in 12, but on the second dataset (26 subjects) per-user normalization increased the gain instead of reducing it, so the interaction depends on the data. Only five of 50 published WESAD studies state which data were used for normalization. Reporting this choice is necessary to separate first-use performance from performance after calibration.

Haochen Chai, Xinbi Luo, Zining Liu +1

College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China

Self-Supervised Pre-Training Affective Computing

Sep 30, 2026cs.CV

Image Classifiers are Efficient Self-Supervised Video Representation Learners

We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of relying on heavy 3D architectures or reconstruction-based autoencoders for learning with unlabeled data, we repurpose standard image Vision Transformers by representing videos as super images which are grids composed of frames sampled from videos. From each super image, we construct two views: one with spatial patch masking and the other with temporal frame masking, ensuring no information leakage across frames. A shared Vision Transformer (ViT) encoder aligns their embeddings using a masked Siamese loss, capturing both motion and appearance cues without reconstruction. Our decoder-free formulation leverages an image foundation model towards efficient video representation learning. Starting from pretrained DINO-v3 and DeiT-v3 image encoders, VideoMSN achieves state-of-the-art performance on Kinetics-400, UCF101, and HMDB51 while requiring up to

32\times

fewer and

160\times

fewer video pretraining epochs compared to prior video self-supervised learning methods. Our proposed approach also shows strong performance in low-shot classification, confirming the transferability of the learned representations in a label-scarce scenario. Project Page: https://cvir.github.io/projects/videomsn.

Owais Iqbal, Sudipta Sarkar, Shyam Marjit +3

Indian Institute of Technology Kharagpur, India · Indian Institute of Science Bangalore, India · École de technologie supérieure Montreal, Canada

Self-Supervised Pre-Training Video Representation Learning

Sep 30, 2026cs.LG

VANDAM: Viewing a nucleotide sequence with DNA molecular priors

Contemporary Genomic Foundation Models (GFMs) rely on a DNA-as-a-string paradigm that employs masked token prediction objectives for pretraining. However, this abstraction does not explicitly model the biochemical, structural, and physical properties essential to biological function. Many molecular properties can be estimated from sequence using established biophysical models, so their utility lies not in providing an independent modality, but in introducing priors that training objectives can explicitly exploit. We introduce VANDAM, a framework that extends the training of GFMs with DNA molecular priors. In self-supervised training, VANDAM predicts regional molecular properties from pooled representations. When functional labels are available and can reward retaining molecular priors, local features are additionally injected at the input. VANDAM consistently improves downstream performance across four architecture families and nine held-out genomic tasks by complementing token-based objectives. Probing experiments further demonstrate that the use of molecular priors generalizes to other unseen molecular properties.

Jeremy Levy, Ariel Larey, Yury Nahshan +18

Applied AI Architecture, NVIDIA, Israel. · Worldwide Field Ops, NVIDIA, Israel. · Developer Programs, NVIDIA, Israel. +3

Self-Supervised Pre-Training Genomics Sequence Modeling Molecular Representation Learning

Sep 29, 2026cs.AI

Flattening the Connectome Spectrum: A Spectral Filter for FC Induces a Pretraining Target for fMRI Encoders

Self-supervised pretraining reshaped prediction in language and vision, and brain foundation models (BFMs) inherited its promise. Representations learned from large unlabelled corpora should capture individual functional dynamics and generalise across cohorts. However, kernel ridge regression (KRR) fitted on functional connectivity (FC) matrices still predicts individual phenotypes more accurately than any BFM we tested. In this paper, we show that KRR is weighted by the eigenvalues of the FC which are miscalibrated for phenotype prediction. We apply an efficient spectral filter to recalibrate the eigenvalues of each subject's FC matrix, enabling the model to exploit more inter-individual variance. Across the 5 datasets, 11 parcellations and 6 prediction targets we tested, we match or exceed the KRR baseline. Based on this finding, we then pretrain a small encoder model on about 4,000 hours of fMRI from 162 open datasets, whereby we align the pairwise similarities between the embeddings of recording snippets with those between the recalibrated connectomes. Our model performs on par with the best of the 6 published BFMs we tested while having an order of magnitude fewer parameters. Our encoder performs better than FC on short scans and in smaller cohorts, especially in fingerprinting. We release the pretrained model weights, the code and the pretraining data, preprocessed and parcellated.

Giovanni Marraffini, Victoria Shevchenko, Carlo Alberto Barbano +1

UNITO · MIND

Kernel Ridge Regression Medical Imaging Foundation Models Functional Connectivity Self-Supervised Pre-Training fMRI Foundation Models Spectral Methods

Sep 29, 2026cs.AI

Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients

Can a population of neural networks develop a useful division of labor without a shared gate or gradients between agents? We study a setting where each network has its own weights, trains independently on the same heterogeneous data, and can ask another agent for help through a forward pass. Unlike mixtures of experts, where a jointly trained gate assigns inputs to experts, specialization here must emerge without central control. We test this in a small scale proxy for predictive visual pretraining. Initially identical agents are finetuned on an unlabeled mixture of six visual domains using masked prediction of frozen DINOv3 features. We measure specialization by asking whether the best agent for an input aligns with its latent domain, and utilization by asking whether responsibility is distributed across agents. We progressively remove central control, ending with DISCO (DIStributed COllaboration) where each agent locally selects a helper, reads its internal state through a gradient free channel, and rewards its router only for the improvement that help provides. Specialization emerges and is useful. Randomly routed populations underperform a single generalist, while semantically routed populations outperform it, showing that specialization rather than population size drives the gain. Specialization persists without a central router, and gradient free communication lets nonexperts exploit emergent expertise. In DISCO, a random agent helped by the expert matches the solo generalist, while experts surpass it, including on data outside the specialization mixture. Local routers select the emergent expert for 98% of inputs. These effects persist across population size, model capacity, data imbalance, and finetuning seeds, providing measurable evidence for the dynamics needed by decentralized predictive pretraining.

Aram Davtyan, Pablo Acuaviva, Sebastian Stapf +1

u b University of Bern Computer Vision Group, Institute of Computer Science University of Bern, Switzerland

Self-Supervised Pre-Training Multi-Agent Collaboration

Sep 28, 2026cs.CV

Handwritten Text Recognition Lives in the High-Pixel Variance Subspace

In self-supervised pretraining for Handwritten Text Recognition (HTR), pixel reconstruction methods outperform contrastive methods, unlike in natural-image classification. We argue that this difference follows from where discriminative signal lies in pixel space: for HTR, it is concentrated in high-variance directions and largely absent from low-variance ones. This predicts that objectives preserving high-variance pixel content will transfer best. We test six SSL methods from three families (pixel-grounded MIM, JEPA, and contrastive) under matched encoder, data, and evaluation protocols on six handwriting benchmarks across five languages. With full labels, pixel-groundrounded SSL achieves the lowest CER on every benchmark and both frozen probes, exposes per-position character information that other families recover only through the readout, and is the only family to benefit from pretraining on real handwriting. Pixel-grounded representations are also more label efficient. Across datasets, encoder alignment with the high-variance pixel subspace predicts CER within every method. With a pretrained LLM decoder, a frozen pixel-grounded encoder is competitive with fully fine-tuned supervised baselines; full fine-tuning achieves the lowest mean CER and ranks first or second on every benchmark. These results show that the value of pixel reconstruction depends on where discriminative signal lies in the input.

Carlos Garrido-Munoz, Jorge Calvo-Zaragoza

University of Alicante, Spain

Self-Supervised Pre-Training Image Reconstruction Online Handwriting Recognition

Sep 24, 2026cs.AI

RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations

Learning surrogates for time-dependent partial differential equations often requires a new simulation corpus when the governing operator changes. We introduce RD-JEPA, a joint-embedding predictive architecture for self-supervised pretraining on reaction-diffusion trajectories. A single model is pretrained on five parameterized systems and then adapted to three held-out systems whose reaction operators and trajectories are excluded from pretraining. Using one, five, or ten complete trajectories from a held-out system, RD-JEPA achieves lower mean relative discrete

\ell^2

field error and mean absolute spatial first-difference error than five supervised surrogate baselines, an independently trained control that removes the trajectory-dependent predictive latent pathway, and an architecture-matched model trained from scratch. Within the evaluated equations, output resolution, forecast horizons, and choices of adaptation trajectories, the results indicate that prediction of future-state representations can support data-efficient adaptation across related reaction-diffusion systems.

Chenhao Si, Ming Yan

School of Data Science, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China

Dynamical Systems Self-Supervised Pre-Training Joint-Embedding Predictive Architecture PDE Surrogate Modeling Transfer Learning

Sep 22, 2026cs.LG

EMGBlend: Heterogeneity-Aware Self-Supervised Pretraining for Gesture and Force Decoding

Public surface electromyography (EMG) datasets vary widely in electrode layout, channel count, frequency support, and size. Simply mixing them for pretraining can misalign channel semantics, introduce spectral targets that some devices cannot observe, and let large or high-channel-count datasets dominate learning. We introduce EMGBlend, a self-supervised framework designed around these differences. It combines shared channel patches with geometry-aware attention, restricts spectral targets to each recording's supported frequency band, and balances exposure across data sources. We pretrain a 109M-parameter model on 11 public EMG sources and evaluate it on gesture recognition, continuous-force regression, and contact classification. EMGBlend consistently outperforms matched random initialization and waveform reconstruction controls. Fixed-budget source controls show that multi-source pretraining improves gesture recognition and remains competitive for force decoding. Ablations confirm that geometry, band-aware targets, and source balancing each contribute to transfer, although cross-person NinaPro force estimation remains difficult. Overall, EMGBlend shows how heterogeneous EMG datasets can be combined through explicit mechanism design rather than simple concatenation. Code is available at https://github.com/tamanano/EMGBlend

Yuwei Jia, Cheng Zhong, Jinyang Yu +1

Beijing University of Posts and Telecommunications, China · Dexwise, China · Shenzhen University, China

EMG-Based Gesture Recognition Self-Supervised Pre-Training Self-Supervised Time Series Representation Learning Transfer Learning

Sep 22, 2026cs.LG

A JEPA Recipe for Tabular Foundation Models

Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeCun, 2022; Assran et al., 2023). On a tabular foundation-model prior, the latent term of a joint-embedding predictive architecture (JEPA) collapsed in our earlier runs and took the encoder with it to a constant map. We report a recipe under which the latent term survives to convergence beside the value objective: the value head reads the encoder field rather than the predictor, and the target is an exponential moving average (EMA) difference. To bound its cost against the value-only arm, both arms train until a plateau rule stops them, with no fixed step budget. A fixed horizon had confounded a slowdown with a ceiling, since the value-only arm was still improving well past the usual budget. At convergence, in one run per arm, the JEPA arm trails the value-only arm across 147 real datasets, 32:70 wins to losses on classification (29:63 with one entry per dataset name) and 8:24 on regression, the margin small on classification and wider on regression, and the count leans the same way in each stratum and each benchmark. The JEPA arm (jepa) needs 1.42 times as many steps as the value-only arm (ds), and 1.66 times its wall-clock, to reach its plateau.

Mingyu Jeon, Suwan Cho, Jae Young Suh

Modulabs, Seoul, Republic of Korea

Tabular Foundation Models Self-Supervised Pre-Training Joint-Embedding Predictive Architecture Predictive Representation Learning Tabular Prediction

Sep 21, 2026cs.CV

Toward a foundation model for forest point clouds

Forest inventories increasingly rely on artificial intelligence (AI) models to derive forest attributes from large-scale 3D point clouds. Current models are typically specialized to a single task, sensor, and forest type, making adaptation expensive in terms of annotations, computation, and expertise. We ask whether a single pretrained model can instead learn transferable representations across diverse forest inventory settings. Inspired by recent developments in language modelling and computer vision, we take a step toward a foundation model (FM) for 3D forestry. Using LitePT as backbone, we first establish a strong supervised baseline that sets a new state of the art on forest semantic and instance segmentation, tree species classification, and age regression benchmarks. We then curate a large-scale unlabelled corpus spanning airborne, UAV, and mobile laser scanning across diverse forest ecosystems, and pretrain the same backbone using self-supervised learning. We systematically evaluate representation learning strategies by comparing training from scratch, supervised pretraining, and self-supervised pretraining across four representative forestry tasks, under varying annotation budgets. Compared with training from scratch, self-supervised pretraining accelerates model convergence and consistently improves performance when annotations are scarce. Compared with task-specific supervised pretraining, self-supervised pretraining yields more transferable representations across downstream forestry tasks. These findings identify the practical regime in which pretrained representations are most valuable and suggest that instance discrimination, rather than forest semantics, is the main remaining obstacle to a general-purpose 3D forest foundation model. Code and models are available at: https://github.com/prs-eth/ForPT.

Yuanwen Yue, Stefano Puliti, Damien Robert +7

ETH Zurich · University of Oxford · Norwegian Institute of Bioeconomy Research (NIBIO) +1

3D Foundation Models Point Cloud Classification Self-Supervised Pre-Training 3D Semantic Segmentation Point Cloud Understanding 3D Instance Segmentation

Sep 15, 2026cs.LG

Procedural Pretraining for Molecular Property Prediction

Molecular property prediction is often limited by the small size of labeled downstream datasets, motivating pretraining on large corpora of unlabeled molecules. In this work, we ask whether useful inductive biases can instead be learned from abstract, procedurally generated data before a model sees any molecular data. We introduce a three-stage training pipeline consisting of procedural pretraining, molecular pretraining on SMILES, and downstream fine-tuning, and evaluate several procedural tasks spanning sequence structure, cellular automata, and graph reasoning. We find that procedural pretraining can improve molecular property prediction even after subsequent molecular pretraining: on Lipophilicity, \textsc{Reverse} reduces test error by 4.8%. For context, the magnitude of this improvement is roughly 90% of the performance difference between our 250K-molecule baseline and the publicly released MoLFormer checkpoint pretrained on approximately 100M molecules. Our analysis shows that the benefit is strongest under downstream data scarcity, depends on the structure of the procedural data rather than only surface-level statistics, and does not increase monotonically with additional procedural training. Instead, transfer typically peaks at an intermediate procedural budget and deteriorates as the model approaches convergence on the procedural task. We further find that, for several tasks, much of the transferable information is localized in the attention layers, while feed-forward layers can contribute to over-specialization. These results show that procedural data can provide transferable structure for molecular learning and offer a complementary route to improving performance when labeled molecular data are limited.

Moritz Friedemann, Zachary Shinnick, Philip Torr +1

University of Oxford · Adelaide University · Slater Labs

Synthetic Data Pretraining Self-Supervised Pre-Training Transfer Learning Molecular Property Prediction

Sep 15, 2026hep-ex

Similarity Pairing with Energy Mover's Distance for Self-Supervised Pre-Training at the LHC

Many self-supervised methods for training foundation models at the Large Hadron Collider (LHC) rely on data augmentations to encourage the model to embed events into a representation space invariant to certain physical or detector symmetries. A common challenge arises from the large freedom in choosing a proper set of augmentations on which downstream performance depends. The implementation of augmentations involves either modifying existing events, potentially breaking the event fidelity, or simulating more event variants, which is computationally intensive. In this work, we present a data-driven method of pairing events by their similarity via the energy mover's distance (EMD), which measures how similar two events are in terms of the work required to transform one into the other. With this approach, distinct events are sampled and matched by their similarity to serve as views for learning invariance, keeping the physics content of each event intact without handcrafted distortions. We demonstrate this augmentation-free pairing method by pre-training on QCD jets via self-distillation and show that it can yield semantic jet embeddings with downstream discrimination power comparable to or better than an augmentation-based baseline.

Ho Fung Tsoi, Dylan Rankin

Department of Physics and Astronomy University of Pennsylvania, USA

Representation Learning Self-Supervised Pre-Training High-Energy Physics

Sep 15, 2026cs.CV

MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Tracking

Large-scale pre-training has transformed representation learning in 2D vision, yet its transferability to 3D single object tracking (SOT) remains insufficiently understood. Directly fine-tuning self-supervised 3D encoders, such as masked autoencoders (MAE), often leads to sub-optimal adaptation because the reconstruction objective is not fully aligned with the spatial-temporal matching requirements of tracking. In this paper, we observe that this difficulty can be interpreted as a layer-wise transfer mismatch: shallow layers tend to preserve transferable geometric cues, while deeper layers become increasingly specialized to the reconstruction pretext task and are less suitable for downstream tracking. Based on this observation, we propose MAETrack, a lightweight adaptation framework for transferring pre-training MAE representations to 3D SOT. MAETrack includes Layer-Selective Initialization (LSI), which initializes only the shallow stages of the tracking backbone from pre-trained weights while re-initializing deeper stages, and Geometric Residual Gating (GRG), which reinforces structurally salient regions in the search BEV features before template-search fusion through residual spatial modulation. Extensive experiments on standard 3D SOT benchmarks show that MAETrack consistently improves upon vanilla fine-tuning baselines with limited computational overhead. More broadly, our results suggest that effective transfer from 3D reconstruction pre-training to 3D tracking is not merely a matter of partial fine-tuning, but depends on a tracking-oriented transfer principle that preserves shallow geometry while adapting deeper representations to the downstream objective.

Sifan Zhou, Qiwei Wang, Linyue Tan +3

School of Automation, Southeast University, Nanjing, 210096, China · Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Nanjing, 210096, China · Harbin Institute of Technology Shenzhen, Shenzhen, 518000, China +1

Masked Autoencoders Self-Supervised Pre-Training Visual Object Tracking Transfer Learning

Sep 15, 2026cs.CV

Which Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasound

Self-supervised learning (SSL) can reduce the need for labelled medical images, but the choice of pretext objective remains unclear for lung ultrasound (LUS). Contrastive learning, masked reconstruction, and joint-embedding predictive architectures (JEPA) differ in the space in which their targets are defined, yet existing ultrasound studies compare them under different corpora, backbones, and evaluation protocols. We compare these three objective families using the same encoder backbone, pretraining corpus, optimisation schedule, and frozen-evaluation protocol. Encoders are pretrained on COVID-BLUeS LUS videos and evaluated with linear,

k

NN, and attentive probes at 5%, 10%, 50%, and 100% label budgets. Evaluation is performed on POCUS using patient-level five-fold cross-validation and on the independently acquired Mendeley-Uganda dataset, which is excluded from both pretraining and probe fitting. At the full label budget under linear probing, VideoMAE and V-JEPA achieve

66.5 \pm 13.1

and

65.4 \pm 11.7

balanced accuracy on POCUS, while MoCo achieves

42.1 \pm 1.2

. On Mendeley-Uganda, the ranking reverses: MoCo performs best at

62.7 \pm 1.0

, followed by VideoMAE at

53.8 \pm 2.8

, while V-JEPA falls near chance at

35.1 \pm 4.9

. These results show that POCUS probe accuracy alone does not identify the objective that transfers best across datasets. We also outline planned representation-level analyses to examine this reversal. Code is publicly available at https://github.com/moeinheidari7829/LUSVideoSSL.

Moein Heidari, Junbo Rao, Jai Choraria +3

University of British Columbia, Vancouver, BC, Canada · Rutgers Cancer Institute of New Jersey, New Brunswick, NJ, USA

Contrastive Learning Masked Autoencoders Self-Supervised Pre-Training Joint-Embedding Predictive Architecture Ultrasound Imaging Medical Image Representation Learning

Sep 14, 2026cs.HC

BRIDGE-EEG: Bridging Self-Supervised Pretraining and Efficient Deployment for Cross-Dataset EEG Classification

The growing use of electroencephalography (EEG) motivates automated analysis that is accurate, transferable, and deployable on constrained hardware. Recent EEG foundation models learn general representations from large-scale pretraining, but their size and computational cost limit edge and wearable deployment. We introduce BRIDGE-EEG, an efficient multi-task EEG classification pipeline that preserves the benefits of pretraining while reducing model size. A unified preprocessing scheme maps heterogeneous recordings with different channel counts, montages, and sampling rates to a device-agnostic 62-channel time--frequency representation. We pretrain an SE-ResNet18 teacher (11.84 M parameters) with SimCLR on unlabeled EEG from five heterogeneous datasets, then compress it into SE-ResNet8 (1.56 M) and SE-ResNet4 (0.48 M) students using task-agnostic and task-specific distillation. We evaluate six benchmarks spanning abnormality detection, motor imagery, and emotion recognition. For abnormality detection and emotion recognition, the students achieve accuracy comparable to or better than several recent EEG foundation models with 10--1,000

\times

more parameters. Motor imagery shows a remaining representation gap, highlighting the importance of pretraining diversity. Inference profiling on a server GPU, desktop CPU, and NVIDIA Jetson Orin Nano shows up to 3.0

\times

lower edge energy per inference (15.64 mJ vs. 46.67 mJ). The compact models further support future deployment on MCU-class wearables.

Meghna Roy Chowdhury, Chengwei Zhou, Haotian Yu +2

Purdue University, Indiana, USA · Case Western University, Ohio, USA

Self-Supervised Pre-Training Edge Inference EEG Emotion Recognition Cross-Dataset Generalization

Sep 14, 2026cs.LG

Geometric-to-Semantic Spherical Transfer Learning for Cortical Sulci Labeling

Deep learning on cortical surfaces faces a dilemma: capturing the complex topology of over 60 nomenclature-dependent sulci per hemisphere requires high-capacity models, yet the extreme scarcity of expert annotations (

N=62

subjects) inevitably causes overfitting. Standard supervised approaches fail to generalize in this data-scarce regime, particularly for variable and small sulci where topological ambiguity is high. To overcome this limitation, we introduce a Geometric-to-Semantic Spherical Transfer Learning framework. First, we leverage massive unlabeled data (UK Biobank,

\approx

30,000 subjects) to pre-train a spherical encoder using a locally-optimized strategy. By relying solely on continuous surface features (curvature and depth), the relevance of this pre-training is confirmed by the model's ability to detect localized and rare topological traits, such as sulcal interruptions. The downstream labeling task, however, introduces extracted sulcal fundi (lines) as an explicit semantic input. To bridge this dimensional domain gap (from purely geometric to semantic) without causing catastrophic forgetting, these anatomical lines are integrated into the pre-trained backbone via a soft-initialized Topological Prior Injector. Our experiments demonstrate that this approach outperforms fully supervised baselines trained from scratch, achieving a mean Dice of 0.77. Crucially, a local analysis reveals that the self-supervised geometric priors yield the largest performance gains on variable and tertiary sulci (up to 14.8%), confirming that learning the cortex shape is highly beneficial for identifying its rarest parts.

Saeb Tounsi, Joël Chavas, Pietro Gori +3

Paris-Saclay University, CEA, NeuroSpin, Baobab, Saclay, France · LTCI, Télécom Paris, Institut Polytechnique de Paris, France

Self-Supervised Pre-Training Geometric Representation Learning Cross-Domain Transfer Learning Neuroimaging Medical Image Representation Learning

Sep 14, 2026cs.CV

Self-supervised Pre-training Helps Retinal Disease Progression Modelling Most When Data Is Scarce

Modelling how a disease progresses over time requires longitudinal imaging cohorts, which are scarce and small, whereas cross-sectional data -- one image per participant -- is abundant. Self-supervised pre-training on such data offers a way to bridge this gap, but it is unclear which strategy best supports progression modelling, or how that answer depends on the amount of labelled longitudinal data. We study this for age-related macular degeneration (AMD), pre-training encoders on the large cross-sectional NAKO cohort and predicting time to late AMD on the longitudinal AREDS dataset. We compare in-house self-supervised encoders against a general-purpose (DINOv2) and a domain-specific (RETFound) foundation model, across contrastive, masked-autoencoding, and self-distillation objectives, under frozen and fine-tuned protocols, and across labelled training sets from 100 to 32,250 examples. Which model performs best depends on how the encoder is used. When the encoder is frozen and labels are few -- the regime typical of longitudinal cohorts -- pre-trained representations reach clinically reasonable discrimination from a few hundred labelled samples, while models trained from scratch do not; this advantage fades under fine-tuning. Transfer is governed by the self-supervision objective rather than corpus scale or domain match, so that an encoder pre-trained on a modest cross-sectional cohort matches or exceeds a far larger in-domain foundation model. Together, these results offer a practical recipe for building progression models where longitudinal data is scarce: a frozen self-supervised encoder with a lightweight survival head.

Ifeoma Veronica Nwabufo, Julius Gervelmeyer, Sarah Müller +1

Hertie Institute for AI in Brain Health, Faculty of Medicine, University of Tübingen, Germany · Tübingen AI Center, University of Tübingen, Germany

Self-Supervised Pre-Training Longitudinal Medical Image Analysis Clinical Outcome Prediction Medical Image Representation Learning

Sep 1, 2026cs.CV

Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison

Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the reference view provides little information for reconstructing non-co-visible patches, implicitly yielding a monocular training signal in these regions. We introduce Gekko, which turns this limitation into a useful signal. The relative improvement of the cross-view reconstruction error over a masked-autoencoder error is a self-supervised proxy for co-visibility: large improvements indicate co-visible regions, negligible ones non-co-visible areas. Gekko is a network, trained from scratch, that jointly performs cross-view completion, masked autoencoding, and per-pixel prediction of this relative improvement, providing an additional binocular signal for all masked regions without any ground-truth 3D annotation. Under identical architectures and training data, Gekko consistently outperforms CroCo on zero-shot correspondence estimation, relative pose estimation, and pointmap regression, with up to 6 times higher accuracy at the strictest relative-pose threshold and a 22% drop in end-point error on ETH3D. The extra channel it learns is itself a strong co-visibility detector on unseen scenes, and Gekko's frozen features outperform released cross-view backbones of comparable or larger size. It can also be trained directly from raw videos with a simple stride-based curriculum, removing the cumbersome 3D preprocessing prior methods require while matching models trained on curated data. Code and pre-trained models are publicly available.

Thibaut Loiseau, Guillaume Bourmaud, Vincent Lepetit

LIGM, Ecole Nationale des Ponts et Chaussées, IP Paris, Univ Gustave Eiffel, CNRS, France · Univ. Bordeaux, CNRS, Bordeaux INP, IMS, UMR 5218, France

Self-Supervised Pre-Training 3D Representation Learning

Sep 1, 2026cs.AI

User Representation via Cross Multi-source Behavior Pre-training for Mobile Games

User representation pre-training has become a fundamental paradigm for alleviating data sparsity in downstream personalization tasks. However, existing studies predominantly focus on single-app or app-level behaviors, overlooking the inherently cross-source and multi-granular nature of user activities on mobile devices. At the device level, user intent emerges from complex interactions among heterogeneous behavior sources and hierarchical action structures, posing challenges that cannot be addressed by conventional app-centric modeling. To tackle this issue, we propose CM-PTM, a novel Cross Multi-source Behavior Pre-Training Model tailored for mobile game user representation learning on device-level behavioral logs. CM-PTM employs hierarchical cascaded mask-then-predict proxy tasks that first infer the source of the next behavior and then progressively refine predictions at the app-action level. This design enables unified modeling of cross-source dependencies and fine-grained behavioral dynamics within a single pre-training paradigm. Extensive experiments on large-scale real-world mobile datasets demonstrate that CM-PTM effectively captures users' endogenous interests and consistently delivers significant performance gains on downstream mobile game recommendation tasks.

Chengqi Yang, Yiran Qiao, Feng Liu +7

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China. · University of Chinese Academy of Sciences, CAS, Beijing, China. · OPPO Research Institute, Shenzhen, China +1

Self-Supervised Pre-Training User Modeling Recommender Systems

Sep 1, 2026hep-ex

Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics

Foundation models are increasingly being pursued in particle and nuclear physics, but existing approaches remain strongly tied to individual experiments through detector-specific architectures or pre-training objectives, limiting their reuse across sensing modalities. We show that a point cloud self-distillation framework yields a substantially more general sensor-level pre-training recipe. We show that the same refined architecture and objective can be independently pre-trained with minimal changes on three qualitatively different detector modalities: liquid argon time projection chamber (LArTPC), collider TPC, and water Cherenkov. Using 1,000 labeled images for downstream task adaptation, Panda V2 matches or exceeds specialized foundation-model baselines trained with orders of magnitude more supervision, matching state-of-the-art particle-clustering performance with 70x fewer labeled events on sPHENIX while substantially improving particle identification, and on LArTPC data matching Panda (arXiv:2512.01324) particle reconstruction with up to 1,000x fewer labels. Beyond reconstruction, simple linear probes reveal physically meaningful latent structure associated with particle causality and track curvature.

Samuel Young, César Jesús-Valls, Kazuhiro Terao

Stanford University · Stanford, CA 94305 · European Organization for Nuclear Research (CERN) +3

Self-Supervised Pre-Training Point Cloud Learning High-Energy Physics

Sep 1, 2026cs.LG

EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection

We propose EEG-VID, a task-guided latent predictive pretraining framework for EEG decoding under session and subject shifts. EEG-VID predicts future latent EEG states from recent history using an exponential-moving-average target encoder and weak task guidance, followed by supervised fine-tuning. Across VIG-48 and BCI Competition IV-2a/IV-2b, Stage 1 improves mean accuracy in 41 of 42 matched backbone-dataset-protocol comparisons, including all 12 leave-one-subject-out settings, with a maximum gain of 16.22 percentage points. On the 48-region cross-day VIG-48 task, EEG-VID achieves 6.52% Top-1 and 30.50% Top-5 accuracy. In a separate six-participant offline robot-scene study, candidate-constrained target selection reaches 40.24% versus a 25% chance level after subject-specific calibration. These results support task-guided latent prediction as a transferable pretraining strategy for EEG decoding and scene-constrained assistive target selection.

Guanzhong Sun, Junyi Ma, Yuxuan Wu +2

School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China · School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China +1

Cross-Subject EEG Decoding Self-Supervised Pre-Training EEG Decoding EEG-Based Visual Decoding Predictive Representation Learning

Aug 31, 2026cs.CV

MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI

Cardiac magnetic resonance imaging (CMR) produces rich sequential data such as temporal cine videos and spatial LGE/mapping stacks, yet most deep learning approaches process individual 2D slices, discarding this context. We present MR-JEPA, a self-supervised video foundation model for CMR that extends LeJEPA to 3D spatiotemporal inputs through tubelet tokenization, spatiotemporal masking augmentation, and initialization from a 2D CMR foundation model. Unlike prior CMR video models limited to cine data, MR-JEPA is pretrained on multi-sequence data (cine, LGE, mapping) from 10,505 patients across two centers without annotations. We evaluate the frozen encoder on six downstream tasks using a unified multi-view gated attention architecture: LV ejection fraction, RV ejection fraction, three myocardial strains (GLS, GCS, GRS), and four-class disease detection. MR-JEPA outperforms other compared methods on all five regression tasks, including both a domain-specific CMR model pretrained on more data with text supervision and a natural-video foundation model, achieving an LV EF MAE of 4.79% (r =0.764) and a GLS MAE of 1.87 (r=0.805), with 21-27% MAE reductions over baselines on strain tasks. For disease detection, MR-JEPA achieved a macro AUG of 0.868, remaining competitive with the domain-specific baseline despite using a fully self-supervised pretraining objective. These results demonstrate the potential of a unified video encoder for robust, multi-view utilization of diverse CMR sequences in clinical cardiac quantification and diagnosis.

Athira J. Jacob, Puneet Sharma, Dorin Comaniciu +1

Digital Technology and Innovation, Siemens Healthineers, Princeton, NJ, USA · Chair for Al in Healthcare and Medicine, Technical University of Munich (TUM) · TUM University Hospital, Munich, Germany +1

Medical Imaging Foundation Models Self-Supervised Pre-Training Medical Image Analysis Medical Diagnosis Video Representation Learning Cardiac MRI

Aug 31, 2026cs.LG

Self-Supervised Pretext Tasks for Infant Cry Analysis: A Controlled Comparison and a Cautionary Result on Donateacry

We compare six self-supervised pretext tasks for infant cry analysis under a fixed budget, meaning the same compact encoder of 1.17M parameters, the same 115 hours of license-verified public pretraining audio, and the same evaluation protocol for every candidate. On cry detection the reconstructive objectives dominate, and a linear probe over a masked-spectrogram encoder reaches 0.988 AUC with subject-wise splits even though the encoder never observed a cry during pretraining. On cry-reason classification over donateacry, the de facto public benchmark for cry reasons, every encoder performs at chance (0.38 to 0.54 macro AUC over 5 classes), and neither domain adaptation on 1.8 hours of real cries nor end-to-end fine-tuning moves the result. Since a frozen HuBERT-base with 80 times more parameters shows the same pattern, the bottleneck must sit in the labels and not in model capacity. We then reproduce the 90%+ accuracies of the donateacry literature on our own system by changing nothing but the evaluation protocol: clip-wise splits raise accuracy to 85.2% (barely above the 83.8% majority-class baseline), and applying augmentation before splitting raises it to 97.9%, matching the reported state of the art, from the same model that measures 0.49 macro AUC under subject-wise splits. Under leakage-free splits, a twentyfold augmentation of the labeled set (vocoder speaker perturbation and noise mixing, 21 hours) leaves cross-subject AUC unchanged: for this task the effective sample size is the number of infants. We release code, seeds and per-clip license manifests.

Luigi Simeone

Independent researcher

Data Leakage Self-Supervised Pre-Training Audio Classification

Aug 13, 2026cs.LG

Into the ORBIT for Time Series: Training Regimes for Foundation Models

Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored. As a result, pre-training distributions are often poorly controlled with respect to domain imbalance, context requirements, prediction horizons, and missingness. We introduce ORBIT (Omni-Range Bootstrap Incremental Training), a training paradigm that makes this distribution explicit and controllable. ORBIT combines Bootstrap Multi-Level Sampling, which controls dataset exposure and samples records, target variables, context windows, and prediction horizons, with Omni-Range Incremental Training, which varies context lengths and prediction horizons throughout a single training stage. Under ORBIT, we train Falcon-2.0, a simple univariate encoder-only Transformer with missingness-aware triple-channel patch tokenization and parallel patch prediction. We further introduce Rank-Guided Cross-Depth Alignment, a training objective that uses late-layer representations as stop-gradient teachers for shallow layers without additional inference cost. Evaluations on GIFT-Eval and fev-bench demonstrate strong zero-shot forecasting performance across diverse domains and frequencies.

Hongjie Xia, Yiding Liu, Yifan Hu +2

Zero-Shot Time Series Forecasting Self-Supervised Pre-Training Curriculum Learning Time-Series Foundation Models

Aug 13, 2026cs.CV

A Controlled Study of Self-Supervised Image and Video Pretraining under Limited Resources

Visual foundation models are a cornerstone of image and video understanding but typically require large amounts of data and computation. The current scale required for pretraining visual foundation models may be unsustainable or unnecessary, and significant benefits arise when effective models can be obtained with fewer resources. To better understand how self-supervised learning (SSL) objectives behave under resource constraints, we conduct a controlled study of image and video SSL objectives under matched data, architecture, and compute budgets. We compare contrastive, reconstruction, feature-prediction, and diffusion objectives and evaluate both standalone and jointly trained image-video SSL formulations across a diverse set of image and video understanding tasks. Our results show that DINOv2-style pretraining consistently provides the strongest overall performance under limited resources. Furthermore, combining DINOv2 with video SSL objectives such as VideoMAE substantially improves image classification and segmentation performance, but degrades video tracking and camera-pose estimation performance, revealing an important tradeoff between semantic and geometric representation learning. These findings suggest that combining image and video SSL objectives can be beneficial in resource-limited settings, while highlighting the need for improved methods that better balance semantic, temporal, and geometric supervision.

Brunó B. Englert, Gijs Dubbelman

Eindhoven University of Technology

Vision Foundation Models Self-Supervised Pre-Training Video Representation Learning Self-Supervised Visual Representation Learning