arXiv:2510.07624v1 Announce Type: new Abstract: Generative models form the backbone of modern machine learning, underpinning state-of-the-art systems in text, vision, and multimodal applications. While Maximum Likelihood Estimation has traditionally served as the dominant training paradigm, recent work have highlighted its…
arXiv:2411.15876v2 Announce Type: cross Abstract: Overfitting remains a significant challenge in deep learning, often arising from data outliers, noise, and limited training data. To address this, the Divide2Conquer (D2C) method was previously proposed, which partitions training data into multiple subsets…
arXiv:2506.10982v2 Announce Type: replace-cross Abstract: Diffusion bridges are a promising class of deep-learning methods for sampling from unnormalized distributions. Recent works show that the Log Variance (LV) loss consistently outperforms the reverse Kullback-Leibler (rKL) loss when using the reparametrization trick…
arXiv:2510.08535v1 Announce Type: new Abstract: Diffusion models are central to generative modeling and have been adapted to graphs by diffusing adjacency matrix representations. The challenge of having up to $n!$ such representations for graphs with $n$ nodes is only partially…
arXiv:2412.17136v2 Announce Type: replace-cross Abstract: Recent advances in MCMC use normalizing flows to precondition target distributions and enable jumps to distant regions. However, there is currently no systematic comparison of different normalizing flow architectures for MCMC. As such, many works…
arXiv:2510.08465v1 Announce Type: new Abstract: Recent advances in supervised learning have driven growing interest in explaining black-box models, particularly by estimating the effects of input variables on model predictions. However, existing approaches often face key limitations, including poor scalability, sensitivity…
arXiv:2210.17478v2 Announce Type: replace-cross Abstract: Adaptive gradient methods have shown their ability to adjust the stepsizes on the fly in a parameter-agnostic manner, and empirically achieve faster convergence for solving minimization problems. When it comes to nonconvex minimax optimization, however,…
arXiv:2510.08409v1 Announce Type: new Abstract: We identify and analyze a surprising phenomenon of Latent Diffusion Models (LDMs) where the final steps of the diffusion can degrade sample quality. In contrast to conventional arguments that justify early stopping for numerical stability,…
arXiv:2505.17838v2 Announce Type: replace Abstract: Transformers robustly exhibit the ability to perform in-context learning, whereby their predictive accuracy on a task can increase not by parameter updates but merely with the placement of training samples in their context windows. Recent…
arXiv:2510.08335v1 Announce Type: new Abstract: Following the wide-spread adoption of machine learning models in real-world applications, the phenomenon of performativity, i.e. model-dependent shifts in the test distribution, becomes increasingly prevalent. Unfortunately, since models are usually trained solely based on samples…
