Stay updated with the latest research and technology news
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,...
arXiv:2601.20221v1 Announce Type: new Abstract: Large language models have achieved strong performance on medical reasoning benchmarks, yet their deployment in clinical settings demands rigorous verification...
arXiv:2601.20223v1 Announce Type: new Abstract: We introduce control models for LLM-powered code completion in JetBrains IDEs: ML classifiers which trigger inference and filter the generated...
arXiv:2601.20224v1 Announce Type: new Abstract: Vision-Language Pre-Trained models, notably CLIP, that utilize contrastive learning have proven highly adept at extracting generalizable visual features. To inherit...
arXiv:2601.20226v1 Announce Type: new Abstract: We present two machine learning frameworks for forecasting aggregated curves and optimizing storage in the EPEX SPOT day-ahead market. First,...
arXiv:2601.20227v1 Announce Type: new Abstract: Inferring physical fields from sparse observations while strictly satisfying partial differential equations (PDEs) is a fundamental challenge in computational physics....
arXiv:2601.20229v1 Announce Type: new Abstract: Service Function Chaining (SFC) requires efficient placement of Virtual Network Functions (VNFs) to satisfy diverse service requirements while maintaining high...
arXiv:2601.20230v1 Announce Type: new Abstract: Full-duplex voice interaction is crucial for natural human computer interaction. We present a framework that decomposes complex dialogue into minimal...
arXiv:2601.20231v1 Announce Type: new Abstract: We study black-box optimization of Lipschitz functions under noisy evaluations. Existing adaptive discretization methods implicitly avoid suboptimal regions but do...
arXiv:2601.20232v1 Announce Type: new Abstract: Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable...
arXiv:2601.20234v1 Announce Type: new Abstract: The scaling law, which indicates that model performance improves with increasing dataset and model capacity, has fueled a growing trend...