arXiv AI September 24, 2026 By Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib

AdaDim: Dimensionality Adaptation for SSL Representational Dynamics

AdaDim introduces a training strategy for self‑supervised learning that adaptively balances dimensionality increase and mutual information reduction. By gradually regularizing the projection head while encouraging feature decorrelation and sample uniformity, AdaDim achieves up to 3% performance gains over standard SSL baselines without relying on costly techniques such as queues or predictor networks. The method demonstrates that optimal SSL models do not simply maximize dimensionality or minimize mutual information, but find a trade‑off between the two.

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.

arXiv Machine Learning

Jun 3

IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension

arXiv:2606. 03338v1 Announce Type: new Abstract: Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data.

By Julie Mordacq, Vicky Kalogeiton, Steve Oudot

arXiv Machine Learning

Jun 2

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation

arXiv:2606. 00514v1 Announce Type: new Abstract: Generative modeling and self-supervised representation learning (SSL) optimize structurally different objectives: generative training rewards distributional fidelity, while SSL rewards semantic coherence.

By Hugues Van Assel, Edward De Brouwer, Saeed Saremi, Gabriele Scalia, Aviv Regev

benchmarks

arXiv Machine Learning

Jun 16

Imbalanced Semi-Supervised Learning via Label Refinement and Threshold Adjustment

arXiv:2407. 05370v3 Announce Type: replace Abstract: Semi-supervised learning (SSL) algorithms often struggle to perform well when trained on imbalanced data.

By Zeju Li, Ying-Qiu Zheng, Chen Chen, Saad Jbabdi

benchmarks safety

arXiv Machine Learning

Jul 21

MTSSL: Meta-Thresholding Semi-Supervised Learning

arXiv:2607. 16363v1 Announce Type: cross Abstract: A large body of Semi-supervised Learning~(SSL) algorithms encounter the threshold $\tau$ to select pseudo-labels.

By Shuyang Liu, Ziang Zeng, Ruiqiu Zheng, Jiazheng Wang, Zechen Liu, Wenxi Li, Zhou Yu

arXiv Machine Learning

Jul 3

Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data

arXiv:2607. 02447v1 Announce Type: new Abstract: Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data.

By Xuanyu Chen, Nan Yang, Shuai Wang, Dong Yuan

safety

arXiv Machine Learning

Jun 5

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

arXiv:2606. 06333v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent feature a single decoder direction, implicitly assuming features to be one-dimensional.

By Seyed Arshan Dalili, Mehrdad Mahdavi

llms efficiency safety

One email a morning, machine-written

Related stories

IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation

Imbalanced Semi-Supervised Learning via Label Refinement and Threshold Adjustment

MTSSL: Meta-Thresholding Semi-Supervised Learning

Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability