Self-Supervised
-
Where, How, and When: Query-Guided Grounding for Video Understanding
2026-10-15 07:32:57Yogesh KumarAbstract
Understanding video content requires reasoning at multiple levels of granularity, from identifying objects to interpreting their interactions and localizing when specific actions occur. This thesis studies three query-guided grounding tasks that answer where key objects are (object-level grounding), how they interact (relationship-level grounding), and when specific moments occur (moment-level grounding). For object-level grounding, we present QDETRv, a query-guided extension of the Detection Transformer for one-shot localization of unseen objects in videos, which combines query-context fusion, a memory module for temporal consistency, and unsupervised pretraining on synthetic object trajectories. We further propose the Temporal Object-Aware Vision Transformer (TOViT) for few-shot video object detection, which builds on a language-aligned open-set vision encoder and propagates high-confidence object features across frames. For relationship-level grounding, we introduce few-shot referring relationships in videos: given a (subject, predicate, object) query and a few support videos sharing the predicate, the entities are localized by optimizing a T-partite random field using a meta-learned relation network with query-conditioned translational embeddings, Global Semantic Aggregation, Local Localization Aggregation, and belief-propagation-based message passing. For moment-level grounding, we propose the Moment Alignment Transformer (MATR) for video-to-video moment retrieval, which uses dual-stage Dynamic Time Warping for pre- and post-fusion alignment, learnable queries for boundary prediction, and self-supervised pretraining with temporal augmentations; MATR also extends to text-to-video moment retrieval with performance comparable to, or better than, the state of the art. These contributions advance query-guided video understanding across spatial, relational, and temporal grounding.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21422
PDF
-
L2GSSL: Label-Efficient Local-to-Global Self-Supervised Learning for Volumetric Healthcare Data
2026-10-15 06:37:47Po-Cheng Cheng, Hung-Hsuan ChenAbstract
Healthcare institutions routinely accumulate high-dimensional computed tomography (CT) volumes, but only a fraction can be annotated by experts. We present L2GSSL, a local-to-global self-supervised learning framework that leverages unlabeled volumes by decomposing pretraining into intra-slice and inter-slice representation spaces. A slice encoder learns view-invariant local features, and a global encoder aggregates the resulting tokens to model volumetric context. The stop-gradient isolates the local space from the global objective, while slice-wise execution and a three-phase schedule support training under constrained GPU memory. On LIDC-IDRI lung nodule malignancy classification, L2GSSL reaches $0.9229$ AUROC with only $10\%$ of the labels and $0.9377$ with $25\%$, exceeding the volume-level VICReg by $0.0229$ and $0.0294$, respectively. With all labels, the strongest supervised baseline exceeds L2GSSL by only $0.0044$ AUROC, consistent with self-supervised pretraining providing its greatest value when annotations are limited. Without adaptation to the external LNDb cohort, a model fine-tuned on $25\%$ of LIDC-IDRI obtains $0.8138$ AUROC and $0.7589$ AUPRC, improving over the strongest evaluated self-supervised baseline by $0.1130$ and $0.0954$. Experiments across data sources, thoracic and abdominal anatomy, downstream tasks, and two backbones examine healthcare-data variety, while lesion-slice masking shows that the predictions depend on lesion-bearing content.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21356
PDF
-
The Density of Thought: Predicting and Steering Reasoning in Large Language Models
2026-10-15 05:31:46Tanush Kalhan, Anupam Chattopadhyay, Sriram Ranga, Amritendu MukherjeeAbstract
We investigate whether variation in information density across chain-of-thought (CoT) reasoning steps predicts answer correctness and can serve as a controllable inference-time target. We prompt frozen pretrained models to solve problems via CoT and measure the density of each reasoning step with two independent metrics: LP variance (how unevenly information is distributed across steps, computed as the variance in mean per-token negative log-likelihood) and the Caveman compression ratio. We then test whether density correlates with, and can be steered to improve, answer correctness. Experiments across six model scales, two training paradigms, and 60 GSM8K problems yield four main findings. First, lower LP variance predicts correctness in supervised fine-tuned (SFT) models, but this relationship weakens with scale and reverses in reinforcement-learning (RL) distilled models. Training paradigm therefore appears more influential than model size in determining density behaviour. Second, synthetic experiments reveal an intrinsic complexity preference: models trained on uniformly distributed data learn complexity-favouring distributions 2.0 to 2.6 times more accurately than simplicity-favouring ones. Third, direct inference-time density steering reduces accuracy from 60.0% to 8.3%, indicating that natural density patterns are functionally important to reasoning. Fourth, pre-generation nudging combining hint injection with contrastive KV-cache steering improves accuracy by 13.3 percentage points, consistent across both metrics. Finally, we introduce Entropy-Gated Density Routing (EGDR), a self-supervised method using token-level Shannon entropy to gate proportional KVcache adjustments during generation, improving accuracy by 10.0 percentage points without any external guidance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21286
PDF
-
Disentangling Depression from Cognitive Decline in Elderly Speech Using Concurrent Clinical Assessments
2026-10-15 04:06:55Woori Jeon, Seunghee Ha, Sang-Kyu Lee, Ji Hye Yoon, Tae-Jin Yoon, Seung Jin Lee, Woojae Han, Jungmin SoAbstract
Detecting depression from speech in elderly patients with mild cognitive impairment (MCI) is complicated by overlapping acoustic effects of cognitive decline. Without disentangling these, classifiers risk learning cognitive rather than depression-specific patterns. We present a Korean elderly speech corpus of 89 MCI speakers collected over three years with concurrent depression (SGDS) and cognitive (MMSE) assessments. Both linear mixed-effects models and partial correlations identify the same pattern: of seven feature groups, only formant features are associated with depression after controlling for cognitive function, while widely used F0 features carry no signal. The F1+F2 subset achieves UAR 0.760 with just 12 features, outperforming both the full eGeMAPS baseline and self-supervised representations. These findings show that concurrent clinical assessments can identify interpretable, depression-specific acoustic markers in populations where cognitive and affective symptoms co-occur.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26890
PDF
-
SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning
2026-10-15 01:42:50Jongann Lee, Sun Woo Park, Yun Young ChoiAbstract
We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks. We prove that standard masking triggers a topological collapse, effectively forcing the model to hallucinate orientation without a reference frame. To resolve this, we introduce SIEVE (Scalar Invariant Extraction Via Equivariance), an SE(3)-equivariant self-supervised framework that compresses point cloud geometry into invariant scalar embeddings. At its core is the spherical projection mask, which preserves global pose while obfuscating local semantics, sidestepping the obstruction by construction. Experiments confirm that SIEVE circumvents the predicted collapse where constant and noise masks fail. On downstream point cloud tasks, the resulting embeddings improve over coordinate-based baselines and hand-crafted geometric descriptors, with the largest gains on generalization to unseen shape categories.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21087
PDF
-
One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness
2026-10-14 17:56:06Artin Tajdini, Manpreet Kaur, Peng QiAbstract
Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leave the underlying task unchanged yet make the agent worse at it. Scoring each sample independently means interface randomization only broadens this dependence from a single interface to the training interface distribution, so out-of-distribution perturbations still degrade the agent. We propose Cross-Interface Policy Regularization (CIPR), a self-supervised objective that replaces action names with uninformative identifiers and presents each training sample under two interfaces in which equivalent actions are identified by construction. CIPR penalizes the KL divergence between the action distributions induced under the two interfaces, so the policy behaves consistently across them. We evaluate CIPR in both supervised and reinforcement-learning post-training, where it improves robustness. On agentic function calling, held-out interface perturbations reduce the accuracy of a post-trained agent by nearly 25%, and CIPR recovers 10.5% while leaving accuracy on the unchanged interface intact.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20576
PDF
-
Generative Representation Learning for Scalable Latent Tokenization
2026-10-14 17:29:09Alan Baade, Kyle Sargent, Vincent Sitzmann, Eric Ryan Chan, Justin Johnson, Li Fei-Fei, Gordon WetzsteinAbstract
We introduce an approach for self-supervised representation learning designed to be used as a tokenizer for generative modeling. Our objective supervises a representation loss by factorizing the pointwise mutual information of the data, which we estimate by taking information differences between conditional predictions from a learned generative model. We justify our algorithm theoretically and empirically, demonstrating that our generative approach to representation learning avoids dimensional collapse and feature suppression in cases where commonly used methods like DINO and LeJEPA fail. Moreover, we show our representation learning technique is scalable; expending more compute leads to predictably better latent tokenization. For the first time, we perform a careful analysis of the combined flop efficiency of tokenizer and generative model and demonstrate that our approach is a compute-optimal improvement over direct diffusion for pixel-space generation, obtaining an FID-50K of 2.18 with JiT-L. Applied to ImageNet and the text-to-image dataset GPIC, we show tokenizer encoder scaling laws for diffusability, where extrapolating our approach achieves representations in 7x fewer FLOPs than DINOv2 on ImageNet and 8x fewer FLOPs than WebSSL on GPIC.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20533
PDF
-
Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages
2026-10-14 15:12:20Stephen Fernandes, Narayan ChoudharyAbstract
India's 22 scheduled languages are spoken by over a billion people in conversations that mix languages, often within one turn, overlap freely, and take place over telephones, in meetings, and in media. Knowing who spoke when, the task of speaker diarization, is essential to speech applications for such conversation: voice agents conversing with several people at once, speaker attributed transcription of meetings and calls, contact center analytics, and media monitoring. We present a systematic study of speaker diarization across all 22 languages on IndicDiarBench and introduce Anuvani-Diarization, which adapts a self-supervised end-to-end segmentation model to Indian conversation with uncertainty aware silver supervision. Evaluated zero shot alongside nine recent diarization systems, it reaches a duration weighted diarization error rate (DER) of 16.78% on all 1,164 recordings, the lowest of all systems we ran and second only to the best published result (16.0%), and leads the three strongest rivals in 14 of 22 languages. It matches its parent on six international benchmarks. We also show that the benchmark's utterance level annotation convention is a hidden variable worth 1.9 to 4.1 DER points, depending on the system, and that a convention learned from other Indian transcriptions does not transfer.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20327
PDF
-
Efficient Test-Time Adaptation For Robot Policies
2026-10-14 15:05:24Motasem Alfarra, Pietro Mazzaglia, Markus Peschl, Daniel Dijkman, Christos LouizosAbstract
Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload changes, sensing degradation), and retraining or manual recalibration is often infeasible under on-device latency and memory constraints. We study test-time adaptation (TTA) for robotic control: adapting a pretrained policy online and in a self-supervised manner during execution, without access to rewards. Our starting point is a lightweight baseline that updates only the actor using a frozen pretrained critic as a deployment-time performance surrogate. Building on this, we introduce TEMPO, a test-time entropy-regularized, memory-guided policy optimization method that stabilizes critic-driven updates under severe shift. TEMPO combines (i) an entropy-promoting regularizer on the critic's predictive distribution to mitigate overconfident extrapolation, and (ii) a score-based memory, inspired by prioritized replay, that prioritizes low-value ("hard") observations and applies importance sampling to focus limited computation on the most informative deployment conditions. Across Go1, Go2, and G1 in MuJoCo Playground under four representative shifts and multiple architectures, TEMPO yields consistent gains, reaching up to 80% improvement in a single-device setting. We further validate on a physical Unitree Go2 with an added calf payload, where fully on-device adaptation improves performance over the non-adapted baseline across real-world episodes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20318
PDF
-
Dataset-Level Regularization for Joint-Embedding Self-Supervised Learning
2026-10-14 13:13:48Konstantinos Almpanakis, Anna KreshukAbstract
Self-supervised joint embedding learning aligns representations of augmented views while regularizing their distribution to prevent collapse. Regularization aims to shape the overall representation distribution, but most joint embedding methods restrict its computation to the active minibatch. We propose out-of-batch regularization, which maintains a dataset-level state in CPU memory and uses globally constructed per-instance targets during minibatch training. Evaluated on natural images and biomedical datasets, these anchors approximate the full-dataset regularization gradient more faithfully than conventional minibatch estimation at small batch sizes. Applications to contrastive (SimCLR) and non-contrastive (SIGReg) approaches show consistent improvement over the corresponding in-batch objectives for image classification, minority-class performance under controlled imbalance, instance retrieval, and continued self-supervised pretraining, with the largest gains at small batch sizes. These results suggest that dataset-level regularization can be decoupled from minibatch optimization, making batch size an optimization choice that does not affect the geometry of the regularizer.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20158
PDF
-
ONCship: A Large-Scale Underwater Acoustic Corpus for Ship Recognition
2026-10-14 07:48:19Zhe Cao, Jichao Zhang, Xiao-Lei ZhangAbstract
Recent advances in deep learning have significantly improved underwater acoustic vessel recognition. However, existing publicly available datasets are typically limited in scale, hindering large-scale representation learning and downstream task evaluation. To address this limitation, we introduce ONCship, a large-scale underwater acoustic dataset comprising 4521 hours of curated recordings from Ocean Networks Canada (ONC) hydrophones and Automatic Identification System (AIS) data. We evaluate the proposed dataset across three tasks: self-supervised representation learning, vessel-type classification, and MMSI-Level Vessel Classification. Experiments on DeepShip and ShipsEar demonstrate the effectiveness of ONCship for acoustic representation learning, with joint pre-training on ONCship and AudioSet achieving a classification accuracy of 62.45% on DeepShip through linear probing. Furthermore, incorporating ONCship as auxiliary training data improves downstream vessel-type classification performance. Beyond conventional vessel-type classification, we further investigate MMSI-Level Vessel Classification, treating each vessel as a distinct identity. Experimental results show that models fine-tuned with different loss functions achieve Top-1 accuracies exceeding 53% and Top-5 accuracies approaching 69%, demonstrating the feasibility of distinguishing individual vessels through MMSI-Level Vessel Classification. Overall, ONCship provides a valuable resource for underwater acoustic representation learning and vessel recognition, while its rich vessel-level metadata enables further exploration of MMSI-Level Vessel Classification.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19722
PDF
-
Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE
2026-10-14 06:04:04Yuhang Hu, Junlin Lyu, Yuan Fang, Xiaoying Shen, Lechen Zhang, Jiong Lin, Judah Goldfeder, Steven Tian, Hod LipsonAbstract
Gaze coordinates attention in human interaction through coupled eye, head, and eyelid motion. A humanoid robot must choose where to look while generating a suitable movement toward that target; fixed tracking rules alone do not model the temporal structure of human gaze. We separate these tasks with an asynchronous vision-language model that selects a scene referent, a reactive perception module that maintains fixation, and a Realistic Gaze Transformer (RGT) that generates target-conditioned motion. RGT is a Transformer-VAE trained on markerless human recordings retargeted to the robot's 11-DoF joint space: self-supervised pretraining encodes recent full-head history, and autoregressive fine-tuning exposes the model to its own predictions during rollout. At inference, a four-dimensional binocular-eye trajectory conditions coordinated neck and eye motion; an auxiliary blink predictor triggers eyelid templates during playback. On a two-second benchmark in which all controllers receive the same ground-truth target, RGT-Base obtains the lowest reported overall seven-joint MSE, and physical demonstrations show the integrated targeting and control pipeline. The evidence establishes robot-space kinematic fidelity and real-time RGT inference; perceived naturalness and open-vocabulary target-selection accuracy remain questions for controlled evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19635
PDF
-
CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesis
2026-10-14 05:33:36Haoxiang Rao, Fang Zhao, Zhao Wang, Weijia Li, Chenyang Si, Caifeng ShanAbstract
Industrial anomaly detection (AD) is bottlenecked by the scarcity of anomalous samples, making high-fidelity anomaly synthesis crucial for improving downstream performance. However, existing methods either rely on scarce real anomaly references or auxiliary data, while lacking complex reasoning and iterative optimization capabilities for generating realistic defects in open-set scenarios. To address these challenges, we propose CORE, a cost-efficient and training-free prompt optimization framework based on Large Multimodal Models (LMMs), which unifies zero-shot and one-shot anomaly synthesis. CORE first introduces an Anomaly Context Grounding module to transform sparse user context into defect-aware generation context, which is subsequently instantiated as structured anomaly prompts that disentangle normal-region preservation from anomaly-specific variation, enabling controllable and faithful defect generation. Furthermore, CORE autonomously refines prompts through a self-supervised contrast-and-reflect mechanism. This design empowers general-purpose LMMs to synthesize realistic anomalies under both zero-shot and one-shot settings without task-specific training. Extensive experiments on MVTec-AD and VisA demonstrate that CORE synthesizes realistic and diverse anomalies, yielding superior improvements in downstream AD performance. Furthermore, its model-agnostic and plug-and-play paradigm enables effortless integration with diverse LMMs, facilitating adaptation to unseen open-set scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19610
PDF
-
IMU-Bench: Benchmarking Wrist IMU Representations Across Kinematic, Semantic and Clinical Tasks
2026-10-14 02:58:38Yiquan Li, Aidan Bradshaw, Chenfeng Gao, Karan AhujaAbstract
Wrist-worn inertial measurement units (IMUs) provide a common sensing modality for tasks ranging from activity and gesture recognition to pose estimation, inertial odometry and clinical motor assessment. Existing wearable benchmarks evaluate performance across multiple tasks, but leave open how supervision for one task affects transfer to others and whether these tasks benefit from a shared representation. We present IMU-Bench, a benchmark of ten tasks from eight datasets for studying IMU multi-task performance and cross-task transfer. We compare six self-supervised methods pretrained on unlabeled recorded and simulated wrist motion, evaluating classification, pose and velocity estimation, and IMU-language retrieval. We find that our masked autoencoder, InrtlWrist, achieves the best or joint-best frozen-probe performance on nine of ten tasks, and fine-tuning improves on training from scratch on nine of ten tasks, including full-body pose, odometry and retrieval. Across transfer and joint-training experiments, supervision that benefits one target can reduce performance on others, with supervised sources transferring within kinematic estimation while, under frozen probing, none approaches the pretrained encoder on language retrieval, and joint-training gains that come at a cost to the paired task. These findings distinguish broad downstream usefulness from complementary task supervision. Code, task cards and a leaderboard are publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19481
PDF
-
LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
2026-10-13 12:08:56Hao Zhang, Yi Huang, Wei Liu, Yuan Gao, Zeju Li, Xu Han, Yu Shi, Ling Zhang, Ke YanAbstract
Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed tomography (NCCT) is increasingly used for opportunistic screening because of its low cost and favorable safety profile. However, downstream tasks such as tumor detection and fine-grained disease diagnosis remain challenging due to NCCT's inherently low tissue contrast, lack of hemodynamic enhancement, and complex anatomical background. These limitations make subtle, heterogeneous, and multifocal hepatic lesions difficult to identify. Although large-scale self-supervised pretraining can learn robust representations from unlabeled NCCT scans, conventional voxel-wise reconstruction does not fully exploit the complementary information available in NCCT. Under weak NCCT contrast, low-level intensity patterns become less informative for pathology recognition, limiting the capture of lesion-specific discriminative features. In this paper, we propose the Liver Frequency-Spatial Unified Self-Supervised Pretraining (LiFUSE). The frequency branch applies random band-stop masking and spectrum reconstruction to encourage the model to capture subtle differences between lesions and surrounding tissues, while the spatial branch performs hybrid-granularity masked volumetric reconstruction to accommodate lesions of diverse sizes and morphologies. Finally, a cross-domain consistency scheme couples the spatial and frequency branches, yielding more discriminative representations for hepatic structures and lesions. Extensive experiments on three clinically relevant tasks across internal cohorts and a public target-domain transfer setting show that LiFUSE consistently outperforms strong baselines. These results suggest that unified frequency-spatial learning can improve liver disease analysis on NCCT, highlighting its potential for large-scale screening.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18243
PDF
-
What Do Deepfake Audio Detectors Hear? From Self-Supervised Models to Audio LLMs
2026-10-13 02:40:30Wanying Ge, Xin Wang, Junichi YamagishiAbstract
Real-world audio recordings for deepfake detection rarely consist solely of speech; they often are mixtures of speech and background events that themselves may also be synthetic. When processing these mixtures, it remains unclear whether detectors attend to the speech or the background event, and where their spectral evidence lies. We study this on the CompSpoof V2 database, whose mixtures pair independently real-or-fake speech and event components. Our results show that all systems detect fake events more accurately than fake speech. However, this performance gap is largely driven by poor generalization to an unseen fake speech domain, rather than a true difference in difficulty. Furthermore, sub-band probing reveals that the front-end encoder dictates where a countermeasure focuses its frequency evidence. To enable reliable deployment in real-world scenarios, future countermeasures should address out-of-domain generalization failures and carefully select front-end encoders aligned with their target acoustic evidence. Our source code and checkpoints are released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17617
PDF
-
Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
2026-10-13 01:52:19Jiaqi Tang, Yu Wang, Yang Liu, Jing Tao, Fandong Zhang, Zhou Zhen, Xiahai Zhuang, Qingchao Chen, Yining Yang, Yizhou YuAbstract
Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols. Models also differ in architecture, pretraining objective and data, while downstream targets range from voxel-level masks to patient-level diagnoses and outcomes. As a result, published findings provide little directly comparable evidence for choosing a model for a new task. Direct comparison of adaptation performance requires fine-tuning candidates on labelled target data, at substantial computational cost. We benchmark 23 candidates across the same 14 segmentation, classification and regression tasks spanning multiple anatomies and modalities. No candidate ranked among the top three across all segmentation tasks or across all classification and regression tasks; a convolutional encoder could outperform a transformer trained with the same objective on one task but underperform it on another. We benchmark transferability estimators against the fine-tuned rankings and find that their agreement varies across dense segmentation, classification and regression. InsightRank uses task-appropriate frozen-feature statistics and architecture-aware pairwise comparisons to rank candidates before fine-tuning. Across the 23-model pool, mean Kendall tau-b was 0.431 for segmentation and 0.352 for classification and regression. The segmentation Top 3 contained a task winner on four of nine tasks; the image-level Top 3 contained none on the five tasks, despite better full-ranking agreement than the matched conventional estimators. A three-model shortlist reduced recorded extraction-plus-training job time by 85.8% across seven segmentation tasks. Together, the benchmark provides a common reference for model selection and InsightRank offers a lower-cost way to prioritize fine-tuning, with shortlist performance that differs by target type.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17573
PDF
-
Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers
2026-10-12 14:01:13Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Andrea Dittadi, Karl Henrik Johansson, Kaitlin Maile, Johannes von Oswald, Stefan BauerAbstract
Progressive depth growth builds large networks by starting with shallow models and inserting layers during training. Recent advances in large language models have renewed interest in this longstanding approach, demonstrating benefits for training efficiency and reasoning alongside changes in internal computations. However, how growing affects representation quality and computational patterns in self-supervised vision transformers remains unclear. In this work, we systematically investigate progressive depth growth in two popular self-supervised families, namely masked autoencoders (MAE) and DINOv3, and analyze how growing affects downstream performance, intermediate representations, and internal computations. Across global and dense tasks, we show that growing improves downstream performance while reducing training FLOPs by 13.9--24.8%, with ImageNet linear-probe accuracy gains of up to 3.36 percentage points. Growing also improves downstream performance at intermediate layers and reshapes internal computational patterns, introducing recurring alternations between global and localized attention in MAE and earlier local-to-global attention progression in self-distilled DINOv3. Together, these findings establish progressive depth growth as an effective and efficient pretraining strategy for improving downstream performance across global and dense visual tasks with less computation, and advance our understanding of how growing shapes visual computation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16817
PDF
-
BehaviorFormer: Discovering Behavioral Patterns via Clusterable Next-Token Prediction
2026-10-12 07:43:23Tobias Schneider, Danial Fahrner, Soren Antebi, Daniel Uedelhoven, Lennard Bodden, Sandra Halscheidt, Rafet SifaAbstract
Discovering behavioral patterns in open-ended games is challenging due to the lack of clear objectives or ground-truth annotations. In this work, we extend a next-token prediction Transformer with the deep clustering algorithm DCSS to learn meaningful representations with well-separated clusters. In a controlled Minecraft session with 26 players, the method discovers 23 distinct behavioral patterns that generalize across the studied players, further refining structures present in self-supervised representations into clearly separable clusters. We group the clusters into seven interpretable categories covering stationary, roaming, travel, mining, base work, logging, and farming behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16322
PDF
-
MP-MNCA: Morphology-Prior Masked Neighbor Cross-Attention for Efficient Spatial Domain Identification
2026-10-12 05:42:01Sidharthan Sivacoumar Chitra, Sanjeev ManivannanAbstract
Spatial transcriptomics jointly captures molecular state, tissue morphology, and spatial organization, yet spatial-domain methods are typically compared only at late training checkpoints, obscuring differences in convergence efficiency. We introduce MP-MNCA, a morphology-prior masked neighbor cross-attention framework that preserves the full 3,000 dimensional highly-variable-gene representation while selectively routing molecular information across spatial neighbors, with histological similarity incorporated as a continuous attention prior under a self-supervised masked neighbor-contrastive objective. Across 12 heterogeneous human dorsolateral prefrontal cortex (DLPFC) sections, MP-MNCA is evaluated against established spatial-domain baselines using both convergence trajectories and epoch-wise spatial-domain visualizations. Our results show that MP-MNCA (i) reaches coherent spatial-domain structure in substantially fewer training epochs, as reflected quantitatively by convergence curves and qualitatively by progressive spatial grids, and (ii) maintains strong clustering quality, achieving a mean peak refined ARI of 0.546 versus 0.549 for the strongest baseline (STAIG), while attaining the highest mean refined NMI of 0.657 versus 0.640. Moreover, MP-MNCA outperforms STAIG on 7 of 12 sections in ARI and 11 of 12 in NMI, demonstrating faster convergence without sacrificing spatial-domain quality.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16212
PDF
