arXiv:2509. 10033v2 Announce Type: replace Abstract: Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms.
arXiv:2606. 02385v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and control.
arXiv:2505. 12532v3 Announce Type: replace-cross Abstract: Efficiently adapting large pretrained models is critical under tight compute and memory budgets.
arXiv:2606. 10975v1 Announce Type: new Abstract: Finding convenient spaces in which certain hypotheses regarding an assumed sparse structure of natural signals hold true has become a desirable result in recent research, its implications being reflected in areas such as data compression, noise reduction and feature extraction.
arXiv:2606. 27941v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) provide useful decompositions of Transformer residual streams, but their learned features are usually named post hoc rather than directly connected to the Transformer's token vocabulary.
arXiv:2606. 15743v1 Announce Type: new Abstract: This paper addresses the missing-modality challenge in multi-modal learning by introducing Unsupervised Learning for Missing Modalities in Multi-Modal Learning (UL4M4), a flexible framework that imputes missing feature embeddings in a task-independent manner before supervised prediction.
arXiv:2606. 31061v1 Announce Type: cross Abstract: Tensor Train (TT) decomposition is a powerful technique for analyzing high-dimensional data.
Dual-energy CT (DECT) exploits attenuation differences across different X-ray spectra to provide richer material information and has been widely used in medical imaging. While sparse-view acquisition can lower radiation exposure, it makes DECT material decomposition even more challenging, as the problem is nonlinear and ill-posed.
arXiv:2602. 08913v3 Announce Type: replace Abstract: In underdetermined regression and classification problems, multiple feature subsets often yield equivalent predictive performance.
arXiv:2607. 17425v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly decodable signals.
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.
MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling, noise, and missing pixels. Building on implicit neural representations (INRs), we introduce a multi-grade coarse-to-fine residual hierarchy that progressively refines the reconstruction across resolution grades, improving representational fidelity and mitigating spectral limitations.
arXiv:2608. 02769v1 Announce Type: cross Abstract: Multimodal supervised learning seeks to leverage multiple heterogeneous data sources to improve predictive performance.