Self-Supervised
-
Retrospective macromolecular pool fraction mapping from conventional clinical MRI: a physics-guided self-supervised deep learning framework
2026-10-27 13:27:34Jelmer van Lune, Miha Fuderer, Oscar van der Heide, Matteo Maspero, Martin B. Schilder, Jan Willem Dankbaar, Stefano Mandija, Alessandro SbrizziAbstract
Macromolecular pool fraction (MPF) is a quantitative imaging biomarker sensitive to myelin integrity and other changes in tissue macromolecular content, but specialized acquisitions and reconstruction methods limit its use in large-scale studies. We present a physics-guided, self-supervised deep learning framework for retrospectively estimating MPF directly from conventional clinical brain MRI ($T_1$-weighted, $T_2$-weighted, and fluid-attenuated inversion recovery [FLAIR]) without paired quantitative reference scans. The framework embeds an analytical two-pool magnetization transfer signal model that related sequence-averaged radiofrequency transmit power to apparent longitudinal relaxation. To accommodate heterogeneous clinical protocols, the network conditions intermediate features on acquisition parameters via adaptive instance normalization. It was trained and evaluated on a multisite, multivendor, multiprotocol dataset of 7,705 MRI sessions (3 T). Across 1,237 test sessions, mean MPF was $0.182 \pm 0.007$ in white matter and $0.144 \pm 0.009$ in gray matter, with limited variation across vendor-by-protocol groups (between-group coefficient of variation: 2.65% and 5.63%, respectively). In 70 sessions with demyelinating-disease labels, MPF was 35.6% lower in segmented lesions than in normal-appearing white matter. MPF maps from two different clinical protocols acquired in a healthy volunteer showed a mean voxel-wise absolute percentage difference of 7.7% and a concordance correlation coefficient of $0.888$, indicating good cross-protocol consistency. These results suggest that magnetization transfer-informed self-supervised learning enables stable MPF mapping from conventional clinical MRI, providing a scalable approach to investigate demyelinating pathology in both existing imaging archives and prospectively acquired conventional clinical scans without dedicated qMT acquisitions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37213
PDF
-
Multibranch Ensemble Head in Vision Foundation Models for Efficient Cucumber Phenological Stage Classification
2026-10-27 12:20:27Kostiantyn KhabarlakAbstract
Vision Foundation Models (VFMs) pretrained with self-supervised learning, such as DINOv2, provide highly transferable features, yet adapting them to small, domain-shifted datasets is still challenging. We propose a regularizing multibranch ensemble head: a training and inference scheme that pairs low- and high-capacity branches, samples a single branch stochastically at each training step, and averages both branches in probability space at inference. The design adds negligible parameters and essentially no inference overhead over a single heavy head, while improving the accuracy-efficiency trade-off under data-scarce conditions. Accurate classification of plant growth stages is critical for precision agriculture, enabling timely decisions on fertilization, irrigation, and harvesting. Therefore, as a challenging practical case we use cucumber phenological stage classification, in which flowers and fruits are frequently occluded by foliage, and stage transitions manifest primarily as subtle changes in leaf morphology. The NALEF Food Safety dataset contains images of five cucumber growth stages captured under diverse real-world conditions. On it we evaluate a broad range of backbones, including DINOv2 and DINOv3 ViT and ConvNeXt variants, against strongly supervised counterparts (ResNet, EfficientNet, ViT). The proposed DINOv2 ViT-S with multibranch head achieves a Macro F1 of 0.978 and Cohen's Kappa of 0.971, matching the performance of models more than ten times larger in parameters and GFlops, while requiring only 12.2 GFlops and 22.3M parameters, making it deployable on smartphones and edge devices for phenological stage classification.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37118
PDF
-
Self-Regularized Flow Language Models
2026-10-27 12:12:42Theodoros Kouzelis, Spyros Gidaris, Nikos KomodakisAbstract
We introduce SERF (Self-Regularized Flow Language Models), a simple self-supervised framework for improving continuous diffusion language models by exploiting the denoising trajectory itself. While continuous flow-based language models offer a promising alternative to autoregressive generation, their training objectives typically rely on supervision from clean target tokens, leaving the denoising trajectory underexploited as a learning signal. SERF addresses this limitation through noisy-to-clean self-distillation: an exponential moving average (EMA) teacher receives a cleaner version of the student's noisy input along the same interpolation path and provides additional supervision. We investigate two variants: SERF-L, which aligns the student's intermediate representations with deeper teacher representations, and SERF-P, which aligns their output token distributions, either at the student's output or at an early student layer. All variants augment the standard training objective without requiring external pretrained models or modifying the inference procedure. Experiments across three continuous language-model paradigms (one-hot FLM, latent ELF, and hyper-spherical S-FLM) demonstrate substantial improvements in training efficiency, generation quality, and few-step generation. In particular, SERF achieves up to 7.7x wall-clock training acceleration on OpenWebText, improves MAUVE by 24.3% and GSM8K accuracy by up to 28.8%, and matches baseline performance with up to 64x fewer sampling steps. These results establish noisy-to-clean self-distillation as an effective approach to improving continuous diffusion language models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37115
PDF
-
Systematic Morphometric Brain Autoencoding for Representation Learning in Neurodegenerative Diseases
2026-10-27 11:36:12Nuria Balb\'as-Esteban, Albert Belenguer-Llorens, Elaheh Moradi, Jussi Tohka, Vanessa G\'omez-Verdejo, Carlos Sevilla-SalcedoAbstract
Early identification of neurodegenerative disorders using structural T1-weighted MRI is essential for timely clinical intervention, yet supervised deep learning models often struggle to generalize due to limited annotations and scanner-induced distribution shift. Self-supervised learning offers a promising alternative; however, existing approaches are largely adapted from natural image paradigms, relying on contrastive objectives or generic masked reconstruction with voxel-wise losses, which may not fully capture the distributed morphometric patterns associated with neurodegeneration. We introduce SYMBA (SYstematic Morphometric Brain Autoencoding), a self-supervised pretraining framework specifically designed for structural brain MRI. SYMBA integrates anatomically constrained masking, a multi-scale structural similarity (MS-SSIM) reconstruction objective, and a progressive curriculum that transitions from local anatomical detail to global brain morphology. These components explicitly incorporate neuroanatomical structure into the self-supervised objective rather than relying on generic image priors. Pretrained on 6,953 T1-weighted MRI scans from nine heterogeneous cohorts, SYMBA is evaluated using frozen linear probing on two independent unseen datasets, enabling a strict assessment of out-of-distribution generalization. Across multiple clinical tasks, SYMBA consistently outperforms recent neuroimaging foundation models, achieving 0.930 AUROC for Alzheimer's disease classification, 0.772 for mild cognitive impairment conversion prediction, and strong performance in amyloid status prediction. In low-label regimes, SYMBA demonstrates high sample efficiency, reaching approximately 0.90 AUROC for AD/CN classification using only six labeled subjects.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37074
PDF
-
Quantized Edge Inference of a Self-Supervised SAR-Optical Encoder on Commodity x86 Hardware
2026-10-27 11:24:25Christian Sanchez-Leon, Dongming ChenAbstract
Self-supervised vision transformers are increasingly used as reusable encoders for Earth observation, but their inference cost on the hardware available in the field is rarely characterized. We deploy a pretrained SAR-optical masked-autoencoder encoder on three commodity x86 nodes, from a low-power CPU without AVX2 to an AVX2+VNNI reference, at FP32, FP16 and INT8 on the CPU and, where present, the integrated GPU, and report latency, energy (RAPL and wall plug) and linear-probe accuracy. Quantization is accuracy-neutral: INT8 changes micro-mAP by only +0.0006, within the seed spread, so precision becomes a pure cost decision. INT8 lowers CPU latency on every node, by 1.45x even on the CPU without AVX2, and CPU energy wherever it is measured, and the VNNI reference (1.53x) suggests a further gain beyond AVX2. The Pareto-optimal device shifts from the integrated GPU, which is 4.38x faster than the CPU on the weakest node, to the CPU as the CPU class improves.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37056
PDF
-
Multi-task Disentangling Fusion Mamba-CNN for MODIS Spectral-Temporal Unmixing with Endmember Variability Modeling
2026-10-27 07:07:54Motasem Alkayid, Yimin Zhu, Naser El-Sheimy, Lincoln Linlin XuAbstract
Spectral-temporal unmixing of MODIS time series is essential for applications such as abundance mapping and spectral library construction, yet it remains challenging due to (i) spectral-temporal information coupling in MODIS data, (ii) intra-class endmember spectral variability and inter-class signature ambiguity, and (iii) the instability of naively fusing multiple expert representations. This paper presents the Multi- task Disentangling Fusion Mamba (MDF-Mamba) to address these limitations. To resolve spectral-temporal coupling, we design a disentangling architecture that pairs per-channel spectral experts with a dedicated bidirectional state-space (Mamba) temporal branch. Convolutional modules each process a single spectral channel, while the Mamba branch encodes the cross-channel seasonal trajectory, forming a multi-branch expert ensemble with soft inter-expert reweighting based on squeeze-and-excitation. For the integration of these spectral and temporal expert outputs, we introduce mHCFusion, adapting the manifold-constrained hyper-connection framework to merge the outputs in a stable and interpretable manner. Endmember variability is addressed by extending the linear mixing model with pixel-wise learnable spectral variability weights that capture intra-class endmember variation. Finally, we design a multi-task training objective that combines supervised abundance estimation with self-supervised spectral reconstruction and endmember regularization terms on the same training data, yielding a highly efficient framework for spectral-temporal unmixing. Experiments on MODIS time series covering the Alberta and Saskatchewan provinces show that MDF-Mamba achieves the best performance on 12 of 14 evaluation metrics across both datasets (7 of 7 on Alberta; 5 of 7 on Saskatchewan), ranking second on the remaining two.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36750
PDF
-
SAGE: Saliency-Annealed Gated Encoder for Universal Vision Recognition
2026-10-27 06:34:00Le Yang, Yucheng Huang, Junyu Chen, Qi Dang, Xin Kong, Haifeng Huo, Qiang ZhaoAbstract
When adapting self-supervised Vision Transformers (ViTs) to dense prediction, existing methods often treat the ViT as a passive feature extractor and may underuse the rich priors encoded in its representations, including saliency, global context, and high-frequency details. We propose SAGE (Saliency-Annealed Gated Encoder), an enhanced ViT-Adapter backbone that explicitly exploits these priors through three complementary innovations: (1) a saliency-guided architecture that extracts DINO-style class-token (CLS) saliency to guide feature gating and high-frequency enhancement, together with dynamic multi-layer aggregation and a local-detail branch; (2) an annealing-based training paradigm designed to improve convergence and feature quality during early training while reducing feature drift later in training; and (3) a two-stage, quality-aware training mechanism that smoothly transitions from focal loss to Varifocal Loss (VFL) within a single training run. Across the evaluated tasks (Fig.~\ref{fig:fig_com}), SAGE achieves state-of-the-art (SOTA) or competitive results on COCO (62.8 box AP and 55.3 mask AP), COCO keypoint estimation (78.5 AP), ADE20K (60.3 mIoU for semantic segmentation and 44.9 mask AP for instance segmentation), TinyImageNet classification (94.76\% Top-1 accuracy), and DIOR-R oriented object detection (78.8 AP$_{50}$). The same backbone is used across tasks, with task-specific decoders. To the best of our knowledge, SAGE is the first framework to achieve multi-task state-of-the-art results on Huawei Ascend NPUs. Code and pretrained models will be released after internal review.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36719
PDF
-
PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement
2026-10-27 04:50:15Tuo Zhang, Alin-Ionut Popa, Yan Xu, Rui Song, Dimitrios DimitriadisAbstract
Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compounding errors over extended horizons. PIVOT (Plan-Inspect-eVOlve Trajectories) addresses this plan-execution misalignment through a self-supervised framework that treats trajectories as optimizable objects iteratively refined via environment interaction. The framework comprises four stages: PLAN generates candidate trajectories; INSPECT executes them and computes structured losses with textual gradients encoding plan-execution discrepancies; EVOLVE applies these signals to produce improved trajectories; and VERIFY performs a final global check against task constraints. A monotonic acceptance process ensures a non-decreasing solution quality. Empirical evaluations on DeepPlanning and GAIA demonstrate state-of-the-art performance: with human-in-the-loop (HITL) feedback, PIVOT establishes a strong upper bound up to 94% relative improvement in constraint satisfaction, while its fully autonomous variant retains substantial gains, showing that the core trajectory-refinement mechanism remains effective without external supervision. At the same time, PIVOT remains computationally efficient, requiring up to 3x to 5x fewer tokens than competing refinement methods. These findings establish that (self- or human-supervised) feedback-based trajectory optimization is a principled methodology for mitigating plan-execution gaps in autonomous agent systems.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11225
PDF
-
Expert lithological labels do not improve learning when used to predict marine sediment properties
2026-10-26 23:43:29John M. Aiken, William Gilpin, Thorsten W. BeckerAbstract
Scientific drilling has produced large archives of physical, chemical and magnetic measurements linked to descriptions of the rock recovered. These archives are mostly incomplete: instruments sample at different intervals, recovery is partial, and destructive analyses preclude later measurement of the same material. We train an self-supervised embedding model on the LILY ocean drilling database using six routinely logged properties (bulk density, magnetic susceptibility, natural gamma radiation, and red, green and blue reflectance) across 236,963 observations from 296 boreholes, with a masked variational autoencoder that has a heteroscedastic Gaussian decoder and learnable mask tokens. The embeddings separate geologist-assigned lithologies as well as a variant trained with those labels, and increasing the weight on the labels degrades reconstruction while leaving classification unchanged. The labels are recoverable from the measurements geologists use to assign them, so training on them adds nothing. Lithological categories compress continuous measurements into classes, and compressing them discards what the measurements record about the processes that produced the rock. The embeddings also predict physical properties that were absent from training, on boreholes the model has never seen. While depth should account for this since sediments compact with burial, it does not. On held-out boreholes depth alone reaches a median $R^2$ of -0.02, against 0.20 for the embedding.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36410
PDF
-
Improving Signals, Declining Encoder: A Known-Answer Test of Label-Free Monitoring in Self-Supervised Learning
Abstract
Self-supervised training is monitored without labels, through the loss and statistics of the learned features. We report a case where we know the encoders lost part of what they had learned, so we can check whether these signals noticed. We trained LeJEPA encoders on synthetic images with known generating factors. In nine of ten seeds, the readability of those factors fell abruptly and stayed down, nearly always along the same direction in factor space. Meanwhile the loss kept falling, and most of the eleven label-free signals we tracked kept improving and rated the declining runs better than runs that did not decline. Standard change-point detection rarely flagged the decline near its onset, and selecting checkpoints by these signals mostly chose ones after it.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35766
PDF
-
Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video Generation
2026-10-26 15:20:53Junyi Chen, Haiyu Zhang, Zhoujie Fu, Tengfei Wang, Chunchao GuoAbstract
Few-step distillation is essential for deploying modern video diffusion models. Among existing approaches, Distribution Matching Distillation (DMD) has emerged as a highly promising paradigm by achieving strong output-space fidelity without adversarial training, while remaining flexible across various student architectures. We observe, however, that DMD fundamentally relies on an output-space objective, lacking explicit regularization on the model's internal representations. As the distillation step count aggressively shrinks, this output-only supervision becomes insufficient, causing the distilled student to degrade in both fine-grained spatial structures and coherent temporal dynamics. To address this limitation, we introduce Self Flow Forcing (SF$^2$), which incorporates a predictive representation loss into the DMD framework without altering its output objective. By providing the student and an Exponential Moving Average (EMA) teacher with heterogeneous noise levels, we establish an information asymmetry. This formulation forces the student to predict the teacher's internal representations from a more corrupted input, effectively integrating self-supervised representation alignment into distribution matching. Extensive experiments demonstrate that SF$^2$ effectively mitigates temporal flickering and consistently improves both spatial fidelity and motion quality. Furthermore, the proposed mechanism is architecture-agnostic - seamlessly supporting both bidirectional and causal models - and requires no external feature extractors, introducing minimal computational overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35594
PDF
-
Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs
2026-10-26 11:50:33Jos\'e Sanz-Dur\'an, David Sol\'is-Mart\'inAbstract
Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under leakage-controlled conditions. We measure it on a corpus of 47 public PHM datasets, harmonized to a single tensor contract and partitioned so that 11 datasets are withheld from pretraining in full. Transfer turns out to be task-dependent: a compact channel-independent Transformer encoder (801,808 parameters) pretrained with masked patch prediction raises fault-classification macro-F1 from 0.350 to 0.812 on CWRU and from 0.569 to 0.951 on HSG18, yet on CMAPSS remaining-useful-life estimation no pretrained checkpoint reliably improves upon a from-scratch baseline. We pretrain under two regimes---centralized, and simulated cross-silo federated with ten clients grouped by physical domain---holding architecture, objective, source data and optimization budget fixed. Two further findings are negative. At matched budget the centralized encoder leads by 15.5--20.2 macro-F1 points in four of four comparisons, although the comparison is confounded by a learning-rate schedule that favours the centralized arm and rests on a single pretraining run per regime; on RUL the two regimes are indistinguishable. And the intrinsic SSL loss is not a valid selection criterion: the centralized encoder more than halves the federated reconstruction loss without a corresponding gap on RUL, and a server-momentum sweep moves downstream validation macro-F1 by up to 0.29 while the SSL loss varies by 0.021. Transfer also hinges on the backbone learning rate: the same checkpoint yields 0.169 or 0.829 macro-F1 on CWRU depending on a single order of magnitude. We release the corpus pipeline, the protocol and the code.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35280
PDF
-
Kronecker-Structured Video Completion with Cross-Fitted Self-Supervised Residual Learning
2026-10-26 09:12:45Qi Qi, Yanfei Wang, Yanjun Cui, Jun-e FengAbstract
Tube-wise video completion reconstructs temporal trajectories at spatial locations unobserved in every frame. We propose a two-stage framework combining regularized masked Kronecker product decomposition (KPD) with cross-fitted self-supervised residual learning. First, we estimate a compact structural backbone directly from observed entries using cyclic component-wise least-squares updates, spatial and temporal factor regularization, and regularizer-optimal scale balancing. The exact updates yield a nonincreasing objective. Second, we address the mismatch between in-sample fitting errors and the prediction errors encountered at missing tubes. We partition observed tubes into folds and construct residual targets using backbone models fitted without the corresponding target tubes. A lightweight 3-D convolutional neural network then predicts corrections from the backbone, visible residual context, observation mask, and local detail features. Exact data consistency preserves observed measurements. Experiments include ablations, sensitivity analysis, grayscale and RGB video completion, and structured missing patterns. Our method achieves the highest mean PSNR and SSIM at the higher tested sampling rates on the grayscale benchmark. On eight selected DAVIS RGB sequences, it achieves the highest mean missing-region PSNR and full-frame SSIM and the lowest mean missing-tube temporal-gradient MAE at every evaluated sampling rate.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35065
PDF
-
AutoPRL: Automated Path Representation Learning via a Learnable View Generator
2026-10-26 08:45:38Sean Bin Yang, Ying Sun, Yunyao CHeng, Hao Miao, Jilin Hu, Bin Yang, Torben Bach Pedersen, Christian S. JensenAbstract
Self-supervised learning has emerged as a powerful paradigm for Path Representation Learning (PRL) in road networks. PRL aims to learn informative representations of paths traversed by moving objects, such as vehicles, where each path consists of a sequence of connected road segments. These representations are essential for various downstream tasks, including travel-time estimation and path ranking. However, existing methods often suffer from ineffective view generation and inefficient training procedures due to their reliance on heuristic augmentations and computationally intensive contrastive learning. To address these issues, we propose AutoPRL, an effective and efficient self-supervised PRL framework that integrates three key components. The Automatic Data Augmentation (AutoDA) module employs variational autoencoders to generate semantically meaningful and diverse feature-level path views by modeling each topology-aware node embedding with a Gaussian latent distribution, thereby mitigating information loss and enhancing representation quality. Second, the Cross-View Decoupled Contrastive (CVDC) learning mechanism improves training efficiency by disentangling the optimization of positive and negative pairs across node- and path-level views, enabling more stable contrastive learning. Third, an Adaptive Co-Training (ACT) module dynamically adjusts uncertainty-based loss weights to balance multiple objectives, ensuring efficient and scalable training. Extensive experiments on three real-world datasets demonstrate that AutoPRL achieves strong and consistent performance in both effectiveness and efficiency across multiple downstream tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35032
PDF
-
Audio-R1: Audio Reasoning through Reinforcement Learning on Self-Supervised Tasks
2026-10-25 22:17:04Jihoon Jeong, Mirco Ravanelli, Zhepei Wang, Cem SubakanAbstract
Reasoning is increasingly important for large audio-language models (LALMs), yet remains relatively underexplored compared with text-only and vision-language models. We introduce Audio-R1, a reinforcement learning (RL) post-training framework that revisits audio self-supervised learning as a source of verifiable rewards for improving audio understanding and reasoning task performance. Audio-R1 uses answers automatically determined during the construction of self-supervised tasks to verify model responses and compute rewards. Experiments across multiple LALMs and diverse audio benchmarks show consistent performance gains, while ablations demonstrate the benefits of each self-supervised task and additional gains from joint training. While both supervised fine-tuning and Audio-R1 improve self-supervised task accuracy, Audio-R1 further improves performance on downstream tasks distinct from the training tasks. These results highlight the potential of RL post-training with self-supervised audio tasks to improve downstream performance and reasoning-trace quality.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34609
PDF
-
AudioFM: Towards General Purpose Audio Representation Learning
2026-10-25 09:35:54Yamin Li, Ruidong Zhang, Anran Wang, Eduardo Fonseca, Dan Ellis, Zechen Li, Simon A. Lee, Tao Pang, Jake Garrison, Maxwell A. Xu, Yicheng Wang, Jitian Zhang, Weizhi Zhang, Haichao Zhang, Catie Chang, Xin Liu, Anupam Pathak, Daniel McDuff, Shwetak Patel, Jake Sunshine, Yuzhe Yang, Xiaoran FanAbstract
Learning audio representations that effectively bridge holistic global soundscapes with fine-grained acoustic moments is a long-standing goal in self-supervised learning. Recording-level contrastive objectives encourage agreement between pooled audio representations, but do not explicitly supervise local time-frequency representations. We introduce AudioFM, a self-supervised framework that combines recording-level contrast with patch-wise masked latent discrimination. Using visible acoustic context, a student predicts representations of masked patches and identifies their corresponding full-view teacher targets among candidates from other recordings. We further incorporate weaker supervision from eligible temporal neighbors to encourage local temporal consistency. Extensive evaluations show that AudioFM achieves state-of-the-art performance across diverse audio domains in linear probing, fine-tuning, and zero-shot transfer, demonstrating superior event detection, robust scene-level understanding, and strong domain generalizability.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34183
PDF
-
Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
2026-10-25 08:18:39Wenhang Shi, Yiren Chen, Zhe Zhao, Jinhao Dong, Wei Lu, Xiaoyong DuAbstract
Reinforcement learning with verifiable rewards (RLVR) enables large language models (LLMs) to continuously self-improve their reasoning capabilities. Compared to RLVR's scalar rewards, recent self-supervised on-policy distillation methods leverage denser supervision signals. However, both paradigms suffer from exploration bottlenecks, struggling to escape local optima when the policy fails to sample valid solutions. Relying on external demonstrations can bypass this issue; however, the off-policy nature hinders genuine self-improvement and the mismatched-distribution reasoning can not be fully exploited. In this work, we propose Self-Evolution Policy Optimization (SEPO), a framework that drives continuous reasoning capability evolution via guided exploration and in-distribution exploitation. Specifically, SEPO utilizes labels to elicit correct reasoning from the policy, unlocking the exploration potential. By treating current policy conditioned on this in-distribution reasoning as a self-teacher, SEPO distills the newly discovered solution back into the policy. Through this iterative cycle of policy-intrinsic exploration and exploitation, SEPO achieves robust and continuous capability evolution. Across scientific, tool-use, and complex logical reasoning domains, SEPO consistently achieves the best performance under identical training time or steps, demonstrating superior efficiency and convergence ceilings. Notably, SEPO maintains stable improvements even in scenarios where baselines severely underperform or fail entirely, such as on complex tasks or with small-scale models. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34137
PDF
-
QECGBERT: A Scalable ECG Foundation Model Based on Self-Supervised Language Learning via VQ-VAE Waveform Tokenization
2026-10-25 00:37:53Aruna Mohan, Burcu Ozek, Or Zilbershot, Fatemeh AfghahAbstract
AI foundation models play a pivotal role in advancing heart disease diagnosis from electrocardiogram (ECG) data, particularly for rare diseases where the lack of sufficient labeled data hinders supervised learning. However, most self-supervised learning methods treat ECGs as generic sequence or image data without exploiting underlying physiological structure. To address this limitation, we propose QECGBERT, a self-supervised ECG language model that explicitly encodes physiological semantics by tokenizing the P, QRS, T, and isoelectric background waveforms. Vector-quantized variational autoencoder (VQ-VAE) tokenization is applied to each 12-lead ECG, with tokens enriched by continuous waveform features to preserve morphology lost during quantization without increasing sequence length. This design enables compact BERT masked language modeling with short sequences, improving scalability and reducing computational cost relative to long-sequence approaches. QECGBERT applies BERT pre-training to the MIMIC-IV dataset containing over 800,000 unlabeled ECG recordings, and fine-tuning on labeled PTB-XL, CPSC2018, and Chapman--Shaoxing--Ningbo datasets for evaluation. The results demonstrate that QECGBERT achieves comparable or superior performance to published benchmarks, offering a scalable, physiologically aware approach to ECG foundation modeling for cardiac diagnosis.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33964
PDF
-
ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models
2026-10-24 17:07:11Xiaoang Zhang, Mert Kiray, Yordanka Velikova, Manoj Biswanath, Benjamin BusamAbstract
Feed-forward 3D foundation models have recently reshaped multi-view reconstruction, yet dynamic 4D understanding still often relies on large-scale motion supervision or hand-crafted, architecture-specific heuristics. We ask whether frozen 3D foundation model tokens already encode motion-relevant information that can be exposed by lightweight readout functions, rather than re-learning motion-specific features with high-capacity decoders. Through probing on three representative backbones, we find that static--dynamic separation is decodable from frozen token representations. Our rank-restricted and spectral analyses on $\pi^3$X reveal that the recovered motion cues are concentrated in a low-dimensional subspace. Building on this, we propose Probing-based Motion Distillation (PMD), which converts pairwise motion-state compatibility scores against a fixed anchor token into dense motion masks. Trained on only 160 YouTube-VOS videos using a single 16 GB GPU, PMD transfers zero-shot to DAVIS, SegTrackv2, and FBMS-59 without target-benchmark fine-tuning. With multi-view pretrained geometric backbones, PMD outperforms training-free heuristics and approaches substantially heavier supervised and self-supervised methods, suggesting that motion decoding from frozen 3D foundation models can be lightweight and data-efficient.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33802
PDF
-
Exploring Joint-Embedding Predictive Architectures for Self-Supervised Representation Learning of Powder X-ray Diffraction Patterns
2026-10-23 21:24:33Ming-Chiang Chang, Brian DeCostAbstract
Powder X-ray diffraction (XRD) is the primary high-throughput method for resolving crystal structures, a cornerstone of materials science. As high-throughput synthesis and self-driving laboratories advance, automated XRD pattern analysis has become vital for accelerating materials discovery. However, traditional matrix factorization methods fail when lattice variations cause non-linear peak shifts. At the same time, supervised learning approaches face a combinatorial explosion when handling multi-phase mixtures. To overcome these challenges, we adopt a self-supervised Joint Embedding Predictive Architecture (JEPA) to learn representation embeddings from 1D diffraction patterns. By optimizing a masked self-prediction loss directly within the latent space, the framework captures high-level crystallographic semantics. Downstream evaluations show that lightweight attentive probes trained on frozen JEPA representations achieve space group classification and lattice parameter estimation accuracy close to much larger supervised vision transformers. Furthermore, latent probing reveals that the learned representation space naturally organizes physical transformations, isolating smooth trajectories for peak broadening. Interestingly, decoding along latent paths between single-phase crystal representations yields realistic multi-phase mixture patterns, demonstrating an emergent continuous structure learned without explicit multi-phase supervision.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33310
PDF
