Stay updated with the latest research and technology news
arXiv:2601.21853v1 Announce Type: new Abstract: Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information...
arXiv:2601.21855v1 Announce Type: new Abstract: In the era of the Internet of Everything (IoE), the exponential growth of sensor-generated data at the network edge renders...
arXiv:2601.21857v1 Announce Type: new Abstract: We present a diffusion-based framework for document-centric background generation that achieves foreground preservation and multi-page stylistic consistency through latent-space design...
arXiv:2601.21859v1 Announce Type: new Abstract: The fundamental trade-off between privacy and utility remains an active area of research. Our contribution is motivated by two observations....
arXiv:2601.21861v1 Announce Type: new Abstract: This paper addresses the critical challenge of coordinating mobile edge UAV networks to maintain robust service in highly dynamic spatiotemporal...
arXiv:2601.21862v1 Announce Type: new Abstract: Infinite words, also known as streams, hold significant interest in computer science and mathematics, raising the natural question of how...
arXiv:2601.21864v1 Announce Type: new Abstract: Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt...
arXiv:2601.21866v1 Announce Type: new Abstract: Real-world multivariate time series can exhibit intricate multi-scale structures, including global trends, local periodicities, and non-stationary regimes, which makes long-horizon...
arXiv:2601.21872v1 Announce Type: new Abstract: Web agents hold great potential for automating complex computer tasks, yet their interactions involve long-horizon, sequential decision-making with irreversible actions....
arXiv:2601.21873v1 Announce Type: new Abstract: Learning systems often expand their ambient features or latent representations over time, embedding earlier representations into larger spaces with limited...
arXiv:2601.21874v1 Announce Type: new Abstract: Differential geometries derived from tensor decompositions have been extensively studied and provided the foundations for a variety of efficient numerical...
arXiv:2601.21876v1 Announce Type: new Abstract: Hybrid planner switching framework (HPSF) for autonomous driving needs to reconcile high-speed driving efficiency with safe maneuvering in dense traffic....
arXiv:2601.21877v1 Announce Type: new Abstract: Benchmark Design in Black-Box Optimization (BBO) is a fundamental yet open-ended topic. Early BBO benchmarks are predominantly human-crafted, introducing expert...
arXiv:2601.21879v1 Announce Type: new Abstract: Given the emergence of Generative AI over the last two years and the increasing focus on Agentic AI as a...
arXiv:2601.21882v1 Announce Type: new Abstract: Graph neural networks (GNNs) are a widely used class of machine learning models for graph-structured data, based on local aggregation...
arXiv:2601.21883v1 Announce Type: new Abstract: Decision-focused learning integrates predictive modeling and combinatorial optimization by training models to directly improve decision quality rather than prediction accuracy...
arXiv:2601.21884v1 Announce Type: new Abstract: Manipulation surfaces control objects by actively deforming their shape rather than directly grasping them. While dense actuator arrays can generate...
arXiv:2601.21885v1 Announce Type: new Abstract: Multi-Objective Evolutionary Algorithms (MOEAs) have proven effective at solving Multi-Objective Optimisation Problems (MOOPs). However, their performance can be significantly hindered...
arXiv:2601.21892v1 Announce Type: new Abstract: Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirical success,...
arXiv:2601.21893v1 Announce Type: new Abstract: Web attack detection is the first line of defense for securing web applications, designed to preemptively identify malicious activities. Deep...
arXiv:2601.21894v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly exhibit strong reasoning abilities, often attributed to their capacity to generate chain-of-thought-style intermediate reasoning. Recent...
arXiv:2601.21895v1 Announce Type: new Abstract: Modern large language models (LLMs) such as GPT, Claude, and Gemini have transformed the way we learn, work, and communicate....
arXiv:2601.21896v1 Announce Type: new Abstract: Video generation is pivotal to digital media creation, and recent advances in autoregressive video generation have markedly enhanced the efficiency...
arXiv:2601.21897v1 Announce Type: new Abstract: Massive multiple-input multiple-output (mMIMO) downlink precoding offers high spectral efficiency but remains challenging to deploy in practice because near-optimal algorithms...