arXiv AI September 10, 2026 By Esteban Rodr\'iguez-Betancourt, Edgar Casasola-Murillo

Hypersolid: Emergent Vision Representations via Short-Range Repulsion

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

safety

arXiv Machine Learning

3d ago

MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis

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...

By Zeyang Huang, Takanori Fujiwara, Angelos Chatzimparmpas, Wandrille Duchemin, Andreas Kerren

arXiv AI

Aug 11

Three Necessary Principles for Self-Supervised Visual Representation Learning

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.

By Nikos Giakoumoglou, Paschalis Giakoumoglou, Tania Stathaki

safety

arXiv AI

Aug 18

Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching

arXiv:2502. 14424v3 Announce Type: replace-cross Abstract: Most self-supervised learning objectives defend against collapse but leave the target representation law unspecified.

By Yuling Jiao, Wensen Ma, Defeng Sun, Hansheng Wang, Yang Wang

fine-tuning benchmarks

arXiv AI

Sep 1

Social-JEPA: Emergent Geometric Isomorphism

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...

By Haoran Zhang, Youjin Wang, Yi Duan, Rong Fu, Dianyu Zhao, Sicheng Fan, Shuaishuai Cao, Wentao Guo, Xiao Zhou

agents efficiency safety

arXiv Computer Vision

Aug 28

DINOcular: Self-Supervised Visuospatial 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.

By Farkhat Almukhamedov, Sami Azirar, Hermann Blum

computer-vision robotics benchmarks

arXiv AI

Jul 7

HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy

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.

By Julius Riel, Vishwa Mohan Singh, Sai Anirudh Aryasomayajula, Anuun Chinbat, Hannes Leonhard, Moritz Ladenburger, Frederik Alexander, Vishisht Choudhary, Fabio Laredo, Giacomo Masserdotti, Thorben Prein, Carsten Marr, Amirhossein Kardoost

rag diffusion computer-vision efficiency

One email a morning, machine-written

Related stories

MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis

Three Necessary Principles for Self-Supervised Visual Representation Learning

Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching

Social-JEPA: Emergent Geometric Isomorphism

DINOcular: Self-Supervised Visuospatial Representations

HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy