The paper introduces a new approach to learning disentangled representations by directly sculpting the aggregate posterior using the non‑parametric Maximum Mean Discrepancy (MMD) and programmable priors. It demonstrates that traditional Variational Autoencoders and Adversarial Training consistently fail to enforce a factorized latent space, as quantified by the Latent Predictability Score (LPS). The proposed method achieves state‑of‑the‑art unsupervised statistical independence, a 70% reduction in entanglement, optional semi‑supervised semantic alignment, and precise shaping of the posterior without compromising reconstruction quality.
arXiv:2606. 05109v1 Announce Type: new Abstract: To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information.
To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information. Learning disentangled representations is a principled way to identify these underlying shared and unique factors that are hidden in observational data.
arXiv:2601. 21688v2 Announce Type: replace-cross Abstract: Disentangled representation learning aims to map independent factors of variation to independent representation components.
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...
DiscoVL introduces a disentangled cross‑modal representation learning framework for vision‑language models, combining orthogonal adversarial regularization with a multi‑branch low‑rank residual aligner to enhance bidirectional visual‑textual interaction. The method decomposes representations into subspaces, enabling cross‑modal feedback at each layer and preventing centroid collapse through an orthogonal adversarial triplet loss. Across 15 benchmarks, DiscoVL consistently outperforms state‑of‑the‑art approaches in base‑to‑novel generalization, cross‑dataset evaluation, and few‑shot 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.
V-Co investigates visual co-denoising for pixel-space diffusion models, using a unified JiT-based framework to isolate key design choices. The study identifies two essential components: a dual-stream architecture with flexible cross-stream interaction and a perceptual-drifting hybrid loss combined with RMS-based feature rescaling for stronger semantic supervision. Experiments on ImageNet-256 demonstrate that V-Co surpasses baseline pixel-space diffusion and strong prior pixel-diffusion methods at comparable model sizes while requiring fewer training epochs.
arXiv:2607. 16725v1 Announce Type: cross Abstract: Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant.
arXiv:2608. 10857v1 Announce Type: new Abstract: Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning.
arXiv:2606. 07646v1 Announce Type: cross Abstract: Test-time adaptation (TTA) aims to align a model to shifting test domains using only unlabeled streaming data.
arXiv:2606. 09725v1 Announce Type: new Abstract: Disentanglement, the separation of factors of variation in data using neural networks, remains a long-standing challenge in machine learning.
arXiv:2606. 21806v2 Announce Type: replace Abstract: Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains.