arXiv:2602.16689v1 Announce Type: cross Abstract: Compositional generalization, the ability to reason about novel combinations of familiar concepts, is fundamental to human cognition and a critical challenge for machine learning. Object-centric (OC) representations, which encode a scene as a set of…
arXiv:2602.15984v1 Announce Type: new Abstract: Flow and diffusion models are typically pre-trained on limited available data (e.g., molecular samples), covering only a fraction of the valid design space (e.g., the full molecular space). As a consequence, they tend to generate…
arXiv:2505.24205v2 Announce Type: replace Abstract: Mixture-of-experts networks (MoEs) have demonstrated remarkable efficiency in modern deep learning. Despite their empirical success, the theoretical foundations underlying their ability to model complex tasks remain poorly understood. In this work, we conduct a systematic…
arXiv:2602.15997v1 Announce Type: new Abstract: Capability emergence during neural network training remains mechanistically opaque. We track five geometric measures across five model scales (405K-85M parameters), 120+ emergence events in eight algorithmic tasks, and three Pythia language models (160M-2.8B). We find:…
arXiv:2510.16161v2 Announce Type: replace Abstract: Modeling irregularly sampled multivariate time series is a persistent challenge in domains like healthcare and sensor networks. While recent works have explored a variety of complex learning architectures to solve the prediction problems for irregularly…
arXiv:2602.16015v1 Announce Type: new Abstract: Conformal prediction provides distribution-free coverage guaranties for regression; yet existing methods assume Euclidean output spaces and produce prediction regions that are poorly calibrated when responses lie on Riemannian manifolds. We propose emph{adaptive geodesic conformal prediction},…
arXiv:2601.11616v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) architectures are widely used for efficiency and conditional computation, but their effect on the geometry of learned functions and representations remains poorly understood. We study MoEs through a geometric lens, interpreting routing as…
arXiv:2602.16020v1 Announce Type: new Abstract: Molecular crystal structure prediction represents a grand challenge in computational chemistry due to large sizes of constituent molecules and complex intra- and intermolecular interactions. While generative modeling has revolutionized structure discovery for molecules, inorganic solids,…
arXiv:2409.17091v3 Announce Type: replace-cross Abstract: In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative augmentation approaches present a promising solution to this issue, having been proven effective…
arXiv:2602.16042v1 Announce Type: new Abstract: As machine learning (ML) continues its rapid expansion, the environmental cost of model training and inference has become a critical societal concern. Existing benchmarks overwhelmingly focus on standard performance metrics such as accuracy, BLEU, or…
