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: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
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
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.
By Mengtan Zhang, Yuchuan Cui, Yu Ma, Zizhan Guo, Wei Ye, Rui Fan
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
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.
By Zhanqi Zhang, Mikio Aoi, Gal Mishne