The paper introduces Hypersolid, a self‑supervised learning objective that uses short‑range repulsion to prevent representation collapse. It combines view alignment with local collision avoidance, creating a latent geometry of compact, semantically aligned neighborhoods with low anisotropy. This geometry improves unsupervised clustering and fine‑grained separation, though it reduces transferability.
arXiv:2601.20173v3 Announce Type: replace Abstract: We present a new nonlinear dimensionality reduction method, MAPLE, that enhances UMAP by improving manifold modeling. MAPLE employs a self-supervis...
arXiv:2608. 08309v1 Announce Type: cross Abstract: We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy.
arXiv:2502. 14424v3 Announce Type: replace-cross Abstract: Most self-supervised learning objectives defend against collapse but leave the target representation law unspecified.
The paper introduces MaSS, a framework that adds a dedicated structural representation pathway to self‑supervised monocular depth estimation. By using a scene‑structure discrimination objective, MaSS learns generalized, layout‑aware structural representations that decouple from contextual features. Experiments on four diverse datasets show MaSS outperforms prior methods and benefits from mixed‑domain training, while zero‑shot tests on eight additional datasets confirm its strong generalizability to out‑of‑distribution scenes.
arXiv:2603.02263v3 Announce Type: replace-cross Abstract: World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such...
NEST is an unsupervised framework that learns a single embedding encoding coarse‑to‑fine cluster structure, optimizing clustering and separation across nested prefix subspaces. The method uses rank and within‑cluster regularization to prevent collapse, and distances in the embedding align more closely with the true hierarchy than the input distances, even though the hierarchy is not provided during training. Experiments on synthetic, vision, text, and single‑cell data show that NEST can recover multiscale structure given only the number of clusters per level, demonstrating its ability to discover multiscale organization in real‑world representations.
DINOcular is a self‑supervised framework that learns joint visuospatial representations from RGB‑D observations. It fuses depth‑derived geometric priors with a visual backbone using inter‑patch and intra‑patch fusion, allowing the model to encode both appearance and spatial structure efficiently. The resulting representation improves 3D awareness on multiple geometry benchmarks while staying competitive on standard RGB‑D semantic segmentation tasks.
arXiv:2607. 04353v1 Announce Type: cross Abstract: Hierarchical structure is common in image data, where fine-grained clusters often merge into larger, coarser semantic groups.
arXiv:2605. 25402v2 Announce Type: replace-cross Abstract: Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging, yet existing methods for ultrasound (US) images operate at the image or frame level, overlooking the anatomical context for clinical-aligned representation learning.
arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.
arXiv:2607. 02404v1 Announce Type: cross Abstract: Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically require large training datasets.
The paper introduces Flow-Based Distribution Matching (FBDM), a non‑adversarial framework that learns self‑supervised representations using explicit geometric references and spherical conditional velocity regression. FBDM assigns augmented image views to shared target references while limiting reference usage, and employs an alignment loss to bring view representations closer. Experiments on datasets from CIFAR to ImageNet demonstrate that FBDM performs nearly as well as adversarial DM, outperforms existing SSL methods, and achieves a 1.48‑ to 1.83‑fold speedup with minimal GPU memory increase, while a theoretical analysis bounds downstream misclassification rates in terms of the pretraining loss.