Many disentanglement methods represent generative factors using Euclidean product coordinates, although the underlying factor spaces may wrap, collapse, or have position-dependent geometry. We introdu...
arXiv:2606. 17531v1 Announce Type: new Abstract: We investigate the learning of interpretable bases in non-negative matrix factorisation (NMF) by regularising the topology of the learned basis functions.
arXiv:2606. 21385v2 Announce Type: replace-cross Abstract: This paper explores unsupervised disentangled representation learning from a functional perspective.
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: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:2511. 21594v3 Announce Type: replace Abstract: Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret.
arXiv:2511. 13899v2 Announce Type: replace-cross Abstract: Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity.
arXiv:2601. 21688v2 Announce Type: replace-cross Abstract: Disentangled representation learning aims to map independent factors of variation to independent representation components.
arXiv:2606. 06342v1 Announce Type: cross Abstract: Topological Data Analysis (TDA) offers a principled, intrinsic lens for comparing neural representations.
arXiv:2606. 02841v1 Announce Type: new Abstract: Deep neural networks learn representations where individual features often lack interpretable meaning; a single neuron may activate for scattered, unrelated inputs.
arXiv:2606. 07058v1 Announce Type: new Abstract: Variational autoencoders (VAEs) learn low-dimensional latent representations of high-dimensional data.