arXiv:2607. 08465v1 Announce Type: new Abstract: I-JEPA and V-JEPA learn by matching latent predictions to target encoder outputs rather than regenerating the original input, and this has worked well for images and video.
arXiv:2607. 09798v1 Announce Type: cross Abstract: Sixth-generation (6G) networks are moving toward AI-native operation, where learning modules are embedded across the radio access network (RAN), edge, and core.
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.
arXiv:2608. 01336v1 Announce Type: cross Abstract: Modern autonomous-driving fleets record far more video than human reviewers can inspect.
The paper investigates whether pretrained image models can generalize to unseen datasets by clustering their embeddings. Using encoders trained only on ImageNet‑1k, both supervised and self‑supervised, the authors evaluate clustering performance on out‑of‑domain images. They find that supervised encoders perform better within the training domain, while self‑supervised encoders excel far outside it, and that fine‑tuning self‑supervised models reverses this trend. Additionally, the study shows that the silhouette score in UMAP‑reduced space correlates strongly with clustering accuracy, offering a proxy metric when labels are unavailable.
arXiv:2605. 18324v2 Announce Type: replace-cross Abstract: Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders.
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.
arXiv:2606. 25225v1 Announce Type: cross Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning.
The study evaluates self‑supervised learning (SSL) models pretrained on ImageNet‑1k and the Human Protein Atlas (HPA) Field‑of‑View (FOV) for protein localization in microscopy images. DINO‑based Vision Transformer backbones pretrained on either dataset transfer well to the OpenCell dataset, achieving strong performance even without fine‑tuning and improving further when fine‑tuned (0.704 ± 0.027 macro F1 on 17 classes). At the single‑cell level, the HPA‑pretrained model outperforms others in k‑nearest‑neighbor classification across all neighborhood sizes (macro F1 ≥ 0.515).
arXiv:2608. 09091v1 Announce Type: cross Abstract: Transfer learning is particularly useful in settings with limited training data, and within image classification it is common to transfer learn upon massive datasets like ImageNet , CIFAR-100, or COCO .
arXiv:2608. 14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features.
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.
arXiv:2609.01014v1 Announce Type: new Abstract: Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enroll...