Stay updated with the latest research and technology news
arXiv:2512.11279v3 Announce Type: replace Abstract: This book invites readers to see mathematics not just as formulas and rules, but as the deepest expression of human...
arXiv:2512.12602v3 Announce Type: replace Abstract: Linear-time attention and State Space Models (SSMs) promise to solve the quadratic cost bottleneck in long-context language models employing softmax...
arXiv:2512.12932v2 Announce Type: replace Abstract: Biological foundation models (BioFMs), pretrained on large-scale biological sequences, have recently shown strong potential in providing meaningful representations for diverse...
arXiv:2512.13698v3 Announce Type: replace Abstract: Admissions systems in many countries struggle to balance merit-based selection with equity objectives. Most existing approaches--categorical quotas, fragmented equity tracks,...
arXiv:2512.14253v3 Announce Type: replace Abstract: In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support both...
arXiv:2512.15586v2 Announce Type: replace Abstract: Recent advances in generative AI have been largely driven by large language models (LLMs), deep neural networks that operate over...
arXiv:2512.15769v2 Announce Type: replace Abstract: The increasing use of generative models such as diffusion models for synthetic data augmentation has greatly reduced the cost of...
arXiv:2512.15973v2 Announce Type: replace Abstract: Dynamic Rank Reinforcement Learning (DR-RL) approximations rely on static rank assumptions, limiting their flexibility across diverse linguistic contexts. Our method...
arXiv:2512.16909v2 Announce Type: replace Abstract: Mobile manipulators in households must both navigate and manipulate. This requires a compact, semantically rich scene representation that captures where...
arXiv:2512.17521v2 Announce Type: replace Abstract: We propose a novel cut finite element method for the numerical solution of the Biot system of poroelasticity. The Biot...
arXiv:2512.18187v2 Announce Type: replace Abstract: Recent query-based 3D object detection methods using camera and LiDAR inputs have shown strong performance, but existing query initialization strategies,such...
arXiv:2512.18405v2 Announce Type: replace Abstract: Data wrangling, the process of cleaning, transforming, and preparing data for analysis, is a well-known bottleneck in data science workflows....
arXiv:2512.18837v3 Announce Type: replace Abstract: We propose Koopman Spectral Wasserstein Gradient Descent (KSWGD), a particle-based generative modeling framework that learns the Langevin generator via Koopman...
arXiv:2512.18921v2 Announce Type: replace Abstract: The present paper introduces concurrency-driven enhancements to the training algorithm for the Kolmogorov-Arnold networks (KANs) that is based on the...
arXiv:2512.19707v2 Announce Type: replace Abstract: The benefits of artificial intelligence (AI) human partnerships-evaluating how AI agents enhance expert human performance-are increasingly studied. Though rarely evaluated...
arXiv:2512.19941v2 Announce Type: replace Abstract: As Vision Transformers (ViTs) become standard vision backbones, a mechanistic account of their computational phenomenology is essential. Despite architectural cues...
arXiv:2512.20063v2 Announce Type: replace Abstract: We introduce $\texttt{PairFlow}$, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiring a...
arXiv:2512.20761v2 Announce Type: replace Abstract: Time Series Foundation Models (TSFMs) are transforming the field of forecasting. However, evaluating them on historical data is increasingly difficult...
arXiv:2512.20806v2 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches...
arXiv:2512.22439v3 Announce Type: replace Abstract: LiDAR-based perception in autonomous systems is constrained by fixed vertical beam resolution and further compromised by beam dropout resulting from...
arXiv:2512.22443v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly reshaping learning paradigms, cognitive processes, and research methodologies across diverse domains. As their adoption...
arXiv:2512.22522v3 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) utilize spike-based activations to mimic the brain's energy-efficient information processing. However, the binary and discontinuous nature...
arXiv:2512.23075v3 Announce Type: replace Abstract: Policy gradient methods for Large Language Models optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a...
arXiv:2512.23126v3 Announce Type: replace Abstract: Direct Preference Optimization (DPO) and its variants have become standard for aligning Large Language Models due to their simplicity and...