In order to understand complex systems such as the human metabolome or human brain, different sensing technologies are used, generating complex data. These datasets are often multiway, i.
arXiv:2608. 13234v1 Announce Type: new Abstract: In order to understand complex systems such as the human metabolome or human brain, different sensing technologies are used, generating complex data.
The paper introduces Coupled Tensor‑Tensor Completion (CTTC), a new framework that incorporates side information in tensor form to enhance tensor completion tasks. CTTC leverages hidden connections among multimodal tensors and is grounded in distance metric learning and group theory. Experiments on the DTD and LINCS datasets show that CTTC outperforms existing methods such as HaLRTC, CTRC, Cell, and NTDDR in both run‑time and root‑sum‑of‑errors accuracy for predicting drug effects.
The paper introduces Coupled Tensor‑Tensor Completion (CTTC), a new framework that incorporates side information in tensor form to enhance tensor completion tasks. CTTC leverages hidden connections among multimodal tensors and is grounded in distance metric learning and group theory. Experiments on the DTD and LINCS datasets show that CTTC outperforms existing methods such as HaLRTC, CTRC, Cell, and NTDDR in both runtime and root‑sum‑of‑squares error for drug effect prediction.
arXiv:2607. 22262v1 Announce Type: cross Abstract: Modeling shared and subject-specific structure in multisubject spatiotemporal data remains challenging, particularly in neuroimaging, where both spatial and temporal patterns exhibit rich variability across subjects.
arXiv:2603.02720v2 Announce Type: replace Abstract: Recently, tensor decompositions have attracted increasing attention. Fundamentally, different interactions among factors induce distinct tensor dec...
arXiv:2601. 18128v2 Announce Type: replace-cross Abstract: High-dimensional data often exhibit variation that can be captured by lower-dimensional factors.
arXiv:2607. 18883v1 Announce Type: cross Abstract: A central aim of unsupervised learning is to uncover latent factors that explain dependencies among observations.
The paper introduces MSAlign, a lightweight model that aligns frozen foundation models for mass spectra (DreaMS) and molecules (MolDeBERTa) to improve metabolite identification from MS/MS spectra. It presents a unified framework for representation alignment and contrastive learning, demonstrates that a score fusion strategy further boosts performance at minimal cost, and addresses evaluation challenges by quantifying distribution shift in data splitting strategies. All resources, including datasets, splits, and code, are publicly released to promote reproducible research.
Monroe is a new molecular foundation model that improves upon existing models by pre‑training on over 81 million molecules from the PM6 quantum chemistry dataset, enhancing stereochemistry representation, and introducing novel training losses such as conformer denoising and embedding decorrelation. It also incorporates a prior‑data‑fitted model (TabPFN) for downstream in‑context prediction and demonstrates superior performance on Polaris benchmarks and activity cliff tests. Ablation studies show that the PFN‑based downstream approach can upgrade other models, producing state‑of‑the‑art variants MiniMol_PFN and CheMeleon_PFN.
Neuro-Causal Factor Analysis (NCFA) reimagines traditional factor analysis by integrating causal structure learning and deep generative modeling. The method learns a directed graph linking latent and observed variables, then trains a deep generative model that respects the graph’s Markov factorization. Experiments on synthetic and real datasets show NCFA achieves lower reconstruction error than standard FA and better latent distribution recovery than a variational autoencoder, while offering a sparser architecture, reduced complexity, and causal interpretability.
arXiv:2312. 07762v3 Announce Type: replace Abstract: Psychiatry research seeks to understand the manifestations of psychopathology in behavior, as measured in questionnaire data, by identifying a small number of latent factors that explain them.
Orthogonal JEPA introduces a latent world‑modeling framework that factorizes predictive states into orthogonal components. By learning basis matrices and dedicated prediction branches, the method reduces redundancy and improves gradient signals for less dominant predictive structures. The factorized states can be synthesized into complete latent representations for downstream tasks such as decoding, planning, or autoregressive rollout, and are evaluated across vision, biology, health, control, and molecular dynamics domains.