arXiv Machine Learning July 27, 2026 By L{\'e}o Nicollier (CB, ATT), Marc Pic (ATT), Pablo Mus{\'e} (CB, IFUMI), Enric Meinhardt-Llopis (CB), Gabriele Facciolo (CB)

Unbiased Open World Regularization for Fair Self-Supervised Learning

Read the original on arXiv Machine Learning →

arXiv:2607. 22149v1 Announce Type: new Abstract: Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset.

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 Machine Learning.

arXiv Machine Learning

Aug 31

Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learning

arXiv:2603.20111v2 Announce Type: replace Abstract: The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emph...

By Moritz G\"ogl, Christopher Yau

rag diffusion benchmarks

arXiv Machine Learning

Aug 27

JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning

JEPAMatch introduces a new semi‑supervised learning framework that replaces traditional output‑thresholding with explicit geometric shaping of latent representations. By combining the FlexMatch loss with a latent‑space regularization inspired by LeJEPA, the method encourages isotropic Gaussian structure in the embedding space, mitigating class imbalance and noisy pseudo‑labels. Experiments on CIFAR‑100, STL‑10, and Tiny‑ImageNet show consistent performance gains and faster convergence compared to existing FixMatch‑based baselines.

By Ali Aghababaei-Harandi, Aude Sportisse, Massih-Reza Amini

rag diffusion computer-vision benchmarks

arXiv AI

2d ago

FairSSL: Fair Multimodal Self-Supervised Learning

arXiv:2508.16748v2 Announce Type: replace-cross Abstract: Prevalent multimodal self-supervised learning (SSL) methods rely on the redundancy assumption: that different views share substantial task-re...

By Jiaee Cheong, Abtin Mogharabin, Paul Liang, Hatice Gunes, Sinan Kalkan

multimodal safety

arXiv Machine Learning

Jun 2

Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\"om Approximation

arXiv:2509. 24467v3 Announce Type: replace Abstract: Self-supervised learning (SSL) learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necessitating domain-specific explanations.

By Maedeh Zarvandi, Michael Timothy, Theresa Wasserer, Debarghya Ghoshdastidar

diffusion benchmarks safety

arXiv AI

Sep 1

Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning

arXiv:2608.30699v1 Announce Type: cross Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...

By Yue Cheng, Jiajun Zhang, Xiaohui Gao, Weiwei Xing, Zhanxing Zhu

efficiency benchmarks safety

arXiv Machine Learning

Jun 17

Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere

arXiv:2606. 17603v1 Announce Type: new Abstract: In Self-Supervised Learning (SSL), preventing representation collapse by explicitly enforcing a uniform distribution on the unit hypersphere has proven to be effective.

By L\'eo Nicollier (CB, ATT), Enric Meinhardt-Llopis (CB), Max Dunitz (ATT), Marc Pic (ATT), Pablo Mus\'e (CB, IFUMI), Gabriele Facciolo (CB)

diffusion safety

One email a morning, machine-written

Related stories

Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learning

JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning

FairSSL: Fair Multimodal Self-Supervised Learning

Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\"om Approximation

Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning

Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere