arXiv:2606. 21806v2 Announce Type: replace Abstract: Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2608. 06427v1 Announce Type: new Abstract: Generative models can reproduce an observational distribution while encoding an incorrect causal structure.
arXiv:2607. 01104v1 Announce Type: cross Abstract: In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance.
arXiv:2401. 04890v2 Announce Type: replace-cross Abstract: This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors.
arXiv:2607. 08254v1 Announce Type: new Abstract: Quantifying variability in a target population relative to a reference population is central to many scientific and clinical problems (e.
arXiv:2608. 01352v1 Announce Type: new Abstract: Estimating causal effects from real-world spatiotemporal data is challenging due to hidden confounders and interference.
arXiv:2606. 17516v1 Announce Type: cross Abstract: Causal discovery from observational data remains challenging due to the need to recover directed structure and latent confounding without interventions.