arXiv:2410.12982v2 Announce Type: replace Abstract: While transformers have been at the core of most recent advancements in sequence generative models, their computational cost remains quadratic in sequence length. Several subquadratic architectures have been proposed to address this computational issue. Some…
arXiv:2505.22422v2 Announce Type: replace Abstract: The construction of confidence intervals for the mean of a bounded random variable is a classical problem in statistics with numerous applications in machine learning and virtually all scientific fields. In particular, obtaining the tightest…
arXiv:2511.07470v1 Announce Type: new Abstract: This work demonstrates “slimmable Neural Amp Models”, whose size and computational cost can be changed without additional training and with negligible computational overhead, enabling musicians to easily trade off between the accuracy and compute of…
arXiv:2511.08500v1 Announce Type: cross Abstract: Large language models (LLMs) adapted to financial domains often suffer from catastrophic forgetting of general reasoning capabilities essential for customer interactions and complex financial analysis. We introduce Selective Parameter Evaluation and Restoration via Model Merging…
arXiv:2511.07484v1 Announce Type: new Abstract: This study presents a novel framework for counterfactual user behavior forecasting that combines structural causal models with transformer-based generative artificial intelligence. To model fictitious situations, the method creates causal graphs that map the connections between…
arXiv:2511.07485v1 Announce Type: new Abstract: Machine learning systems exhibit diverse failure modes: unfairness toward protected groups, brittleness to spurious correlations, poor performance on minority sub-populations, which are typically studied in isolation by distinct research communities. We propose a unifying theoretical…
arXiv:2511.07481v1 Announce Type: new Abstract: This study investigates embedding reconstruction attacks in large language models (LLMs) applied to genomic sequences, with a specific focus on how fine-tuning affects vulnerability to these attacks. Building upon Pan et al.’s seminal work demonstrating…
arXiv:2511.07482v1 Announce Type: new Abstract: Large Language Models require substantial computational resources for inference, posing deployment challenges. While dynamic pruning offers superior efficiency over static methods through adaptive circuit selection, it exacerbates alignment degradation by retaining only input-dependent safety-critical circuit…
arXiv:2511.07473v1 Announce Type: new Abstract: Objective: Electronic health record (EHR) phenotyping often relies on noisy proxy labels, which undermine the reliability of downstream risk prediction. Active learning can reduce annotation costs, but most rely on fixed heuristics and do not…
arXiv:2511.07472v1 Announce Type: new Abstract: We present the Multivariate Variational Autoencoder (MVAE), a VAE variant that preserves Gaussian tractability while lifting the diagonal posterior restriction. MVAE factorizes each posterior covariance, where a emph{global} coupling matrix $mathbf{C}$ induces dataset-wide latent correlations…
