arXiv:2503.01072v2 Announce Type: replace-cross Abstract: The key to VI is the selection of a tractable density to approximate the Bayesian posterior. For large and complex models a common choice is to assume independence between multivariate blocks in a partition of…
arXiv:2510.03255v1 Announce Type: new Abstract: The scientific reasoning ability of large language models (LLMs) has recently attracted significant attention. Time series, as a fundamental modality in scientific data, presents unique challenges that are often overlooked in current multimodal LLMs, which…
arXiv:2510.03257v1 Announce Type: new Abstract: On-demand ride-sharing platforms, such as Uber and Lyft, face the intricate real-time challenge of bundling and matching passengers-each with distinct origins and destinations-to available vehicles, all while navigating significant system uncertainties. Due to the extensive…
arXiv:2510.04285v1 Announce Type: cross Abstract: We introduce a cumulant-expansion framework for quantifying how large language models (LLMs) internalize higher-order statistical structure during next-token prediction. By treating the softmax entropy of each layer’s logit distribution as a perturbation around its “center”…
arXiv:2510.03258v1 Announce Type: new Abstract: Test-time adaptation (TTA) aims to transfer knowledge from a source model to unknown test data with potential distribution shifts in an online manner. Many existing TTA methods rely on entropy as a confidence metric to…
arXiv:2510.04553v1 Announce Type: cross Abstract: We introduce a scalable witness-based persistent homology pipeline for full-brain MRI volumes that couples density-aware landmark selection with a GPU-ready witness filtration. Candidates are scored by a hybrid metric that balances geometric coverage against inverse…
arXiv:2510.03259v1 Announce Type: new Abstract: Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between…
arXiv:2510.04939v1 Announce Type: cross Abstract: The effectiveness of modern deep learning models is predicated on the availability of large-scale, human-annotated datasets, a process that is notoriously expensive and time-consuming. While Active Learning (AL) offers a strategic solution by labeling only…
arXiv:2510.03260v1 Announce Type: new Abstract: Zero-Shot Learning is an important paradigm within General-Purpose Artificial Intelligence Systems, particularly in those that operate in open-world scenarios where systems must adapt to new tasks dynamically. Semantic spaces play a pivotal role as they…
arXiv:2410.23169v2 Announce Type: replace Abstract: Neural collapse (NC) and its multi-layer variant, deep neural collapse (DNC), describe a structured geometry that occurs in the features and weights of trained deep networks. Recent theoretical work by Sukenik et al. using a…
