Stay updated with the latest research and technology news
arXiv:2601.20174v1 Announce Type: new Abstract: Numerical techniques for solving partial differential equations (PDEs) are integral for many fields across science and engineering. Such techniques usually...
arXiv:2601.20175v1 Announce Type: new Abstract: Content-preserving style transfer, generating stylized outputs based on content and style references, remains a significant challenge for Diffusion Transformers (DiTs)...
arXiv:2601.20176v1 Announce Type: new Abstract: Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most...
arXiv:2601.20180v1 Announce Type: new Abstract: Performative prediction captures the phenomenon where deploying a predictive model shifts the underlying data distribution. While simple retraining dynamics are...
arXiv:2601.20183v1 Announce Type: new Abstract: Satellite-based Internet of Things (S-IoT) faces a fundamental trilemma: propagation delay, dynamic fading, and bandwidth scarcity. While Layer-coded Hybrid ARQ...
arXiv:2601.20184v1 Announce Type: new Abstract: The increasing integration of AI agents into cyber-physical systems (CPS) introduces new security risks that extend beyond traditional cyber or...
arXiv:2601.20185v1 Announce Type: new Abstract: X-Codec-2.0 has shown strong performance in neural audio compression and multilingual speech modeling, operating at a 50 Hz latent rate...
arXiv:2601.20191v1 Announce Type: new Abstract: This paper proposes a direct sampling method for the inverse problem of magnetic induction tomography (MIT). Our approach defines a...
arXiv:2601.20193v1 Announce Type: new Abstract: Robust reinforcement learning methods typically focus on suppressing unreliable experiences or corrupted rewards, but they lack the ability to reason...
arXiv:2601.20194v1 Announce Type: new Abstract: With the deep integration of artificial intelligence and smart home technologies, the intelligent transformation of traditional household appliances has become...
arXiv:2601.20196v1 Announce Type: new Abstract: Marine biofouling on vessel hulls poses major ecological, economic, and biosecurity risks. Traditional survey methods rely on diver inspections, which...
arXiv:2601.20198v1 Announce Type: new Abstract: Recent advances align diffusion models with human preferences to increase aesthetic appeal and mitigate artifacts and biases. Such methods aim...
arXiv:2601.20199v1 Announce Type: new Abstract: Item indexing, which maps a large corpus of items into compact discrete representations, is critical for both discriminative and generative...
arXiv:2601.20203v1 Announce Type: new Abstract: Recent work has shown that machine-learned predictions can provably improve the performance of classic algorithms. In this work, we propose...
arXiv:2601.20205v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) layers have emerged as an important tool in scaling up modern neural networks by decoupling total trainable parameters...
arXiv:2601.20206v1 Announce Type: new Abstract: As an important part of urbanization, the development monitoring of newly constructed parks is of great significance for evaluating the...
arXiv:2601.20207v1 Announce Type: new Abstract: We develop a kernel-based approach for estimating the spatially varying Sobolev regularity~$s$ of an unknown $d$-variate function~$f$ from scattered sampling...
arXiv:2601.20208v1 Announce Type: new Abstract: The central challenge in robotic manipulation of deformable objects lies in aligning high-level semantic instructions with physical interaction points under...
arXiv:2601.20209v1 Announce Type: new Abstract: Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging...
arXiv:2601.20211v1 Announce Type: new Abstract: Knowledge about vessel activity in port areas and around major industrial zones provides insights into economic trends, supports decision-making for...
arXiv:2601.20212v1 Announce Type: new Abstract: In this work, we present a first-order unfiltered exponential integrator for the one-dimensional derivative nonlinear Schr\"odinger equation with low regularity....
arXiv:2601.20215v1 Announce Type: new Abstract: Short-video recommender systems typically optimize ranking models using dense user behavioral signals, such as clicks and watch time. However, these...
arXiv:2601.20217v1 Announce Type: new Abstract: We derive an accounting identity for predictive models that links accuracy with common fairness criteria. The identity shows that for...
arXiv:2601.20218v1 Announce Type: new Abstract: Recent GRPO-based approaches built on flow matching models have shown remarkable improvements in human preference alignment for text-to-image generation. Nevertheless,...