Stay updated with the latest research and technology news
arXiv:2505.23463v5 Announce Type: replace Abstract: Several variants of reweighted risk functionals, such as focal loss, inverse focal loss, and the Area Under the Risk Coverage...
arXiv:2506.00614v2 Announce Type: replace Abstract: Real-world multichannel time series prediction faces growing demands for efficiency across edge and cloud environments, making channel compression a timely...
arXiv:2506.00886v2 Announce Type: replace Abstract: As large language models evolve into tool-augmented agents, a central question remains unresolved: when is external tool use actually justified?...
arXiv:2506.01042v3 Announce Type: replace Abstract: Probing large language models (LLMs) has yielded valuable insights into their internal mechanisms by linking neural activations to interpretable semantics....
arXiv:2506.01883v2 Announce Type: replace Abstract: Training deep learning models on single-cell datasets with hundreds of millions of cells requires loading data from disk, as these...
arXiv:2506.03229v3 Announce Type: replace Abstract: In the context of noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels...
arXiv:2506.04877v3 Announce Type: replace Abstract: Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs)...
arXiv:2506.06725v3 Announce Type: replace Abstract: Large Language Models (LLMs) possess general world knowledge but often struggle to generate precise predictions in structured, domain-specific contexts such...
arXiv:2506.06989v2 Announce Type: replace Abstract: Implicit feedback data, such as user clicks, is commonly used in learning-to-rank (LTR) systems because it is easy to collect...
arXiv:2506.07486v2 Announce Type: replace Abstract: Automated test-generation research overwhelmingly assumes the correctness of focal methods, yet practitioners routinely face non-regression scenarios where the focal method...
arXiv:2506.09277v4 Announce Type: replace Abstract: Large Language Models (LLMs) can generate plausible free text self-explanations to justify their answers. However, these natural language explanations may...
arXiv:2506.13821v4 Announce Type: replace Abstract: In this chapter we outline the role that software has in modern society, along with the staggering costs of poor...
arXiv:2506.17254v2 Announce Type: replace Abstract: The rapid pace at which new large language models (LLMs) appear, and older ones become obsolete, forces providers to manage...
arXiv:2506.17357v2 Announce Type: replace Abstract: Local search plays a central role in many effective heuristic algorithms for the vehicle routing problem (VRP) and its variants....
arXiv:2506.18786v2 Announce Type: replace Abstract: Cybersickness remains a critical barrier to the widespread adoption of Virtual Reality (VR), particularly in scenarios involving intense or artificial...
arXiv:2506.19089v4 Announce Type: replace Abstract: We introduce $\texttt{StorySim}$, a programmable framework for synthetically generating stories to evaluate the theory of mind (ToM) and world modeling...
arXiv:2506.20966v2 Announce Type: replace Abstract: Vision-language-action (VLA) models extend vision-language models (VLM) by integrating action generation modules for robotic manipulation. Leveraging the strengths of VLM...
arXiv:2506.21599v3 Announce Type: replace Abstract: Advancing large language models (LLMs) for the next point-of-interest (POI) recommendation task faces two fundamental challenges: (i) although existing methods...
arXiv:2506.24032v3 Announce Type: replace Abstract: In a large-scale network, we want to choose some influential nodes to make a profit by paying some cost within...
arXiv:2507.00875v2 Announce Type: replace Abstract: Hong Kong case law translation presents significant challenges: manual methods suffer from high costs and inconsistent quality, while both traditional...
arXiv:2507.01027v2 Announce Type: replace Abstract: Large language models (LLMs) demonstrate remarkable performance but face substantial computational and memory challenges that limit their practical deployment. Quantization...
arXiv:2507.03147v3 Announce Type: replace Abstract: Along with the explosion of large language models, improvements in speech synthesis, advancements in hardware, and the evolution of computer...
arXiv:2507.03779v3 Announce Type: replace Abstract: Large-scale vision foundation models such as DINOv2 boast impressive performances by leveraging massive architectures and training datasets. But numerous scenarios...
arXiv:2507.04490v2 Announce Type: replace Abstract: Contextual anomaly detection (CAD) aims to identify anomalies in a target (behavioral) variable conditioned on a set of contextual variables...