Stay updated with the latest research and technology news
arXiv:2602.18928v1 Announce Type: new Abstract: Evaluating Large Language Models (LLMs) with respect to real-world code complexity is essential. Otherwise, there is a risk of overestimating...
arXiv:2602.18929v1 Announce Type: new Abstract: Conventional sequential recommendation models have achieved remarkable success in mining implicit behavioral patterns. However, these architectures remain structurally blind to...
arXiv:2602.18931v1 Announce Type: new Abstract: Data centers capable of running large language models (LLMs) are spread across the globe. Some have high end GPUs for...
arXiv:2602.18933v1 Announce Type: new Abstract: In this work, we propose a stochastic gradient descent (SGD) framework to design data-driven policy gradient descent algorithms for the...
arXiv:2602.18934v1 Announce Type: new Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a specific data point was used...
arXiv:2602.18935v1 Announce Type: new Abstract: As libraries explore large language models (LLMs) as a scalable layer for reference services, a core fairness question follows: can...
arXiv:2602.18936v1 Announce Type: new Abstract: Personalized image generation requires effectively balancing content fidelity with stylistic consistency when synthesizing images based on text and reference examples....
arXiv:2602.18937v1 Announce Type: new Abstract: We study structure-preserving Krylov subspace methods for approximating the matrix-vector products f(H)b, where H is a large Hamiltonian matrix and...
arXiv:2602.18940v1 Announce Type: new Abstract: Deep Research Agents generate analyst-grade reports, yet evaluating them remains challenging due to the absence of a single ground truth...
arXiv:2602.18941v1 Announce Type: new Abstract: Vision-and-Language Scene navigation is a fundamental capability for embodied human-AI collaboration, requiring agents to follow natural language instructions to execute...
arXiv:2602.18943v1 Announce Type: new Abstract: Procedural content generation (PCG) has made substantial progress in shaping static 2D/3D geometry, while most methods treat gameplay mechanics as...
arXiv:2602.18946v1 Announce Type: new Abstract: Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains...
arXiv:2602.18947v1 Announce Type: new Abstract: Large scale control of nonplayer agents is central to modern games, while production systems still struggle to balance several competing...
arXiv:2602.18948v1 Announce Type: new Abstract: Transformer models contain substantial internal redundancy arising from coordinate-dependent representations and continuous symmetries, in model space and in head space,...
arXiv:2602.18950v1 Announce Type: new Abstract: In light of today's massive data processing, digital computers are reaching fundamental performance limits due to physical limitations and energy...
arXiv:2602.18951v1 Announce Type: new Abstract: This paper addresses the problem of temporal logic motion planning for an autonomous robot operating in an unknown environment. The...
arXiv:2602.18955v1 Announce Type: new Abstract: Neural Processes (NPs), and specifically Transformer Neural Processes (TNPs), have demonstrated remarkable performance across tasks ranging from spatiotemporal forecasting to...
arXiv:2602.18956v1 Announce Type: new Abstract: We introduce INDUCTION, a benchmark for finite structure concept synthesis in first order logic. Given small finite relational worlds with...
arXiv:2602.18957v1 Announce Type: new Abstract: We introduce EdgeSketch, a compact graph representation for efficient analysis of massive graph streams. EdgeSketch provides unbiased estimators for key...
arXiv:2602.18959v1 Announce Type: new Abstract: Real-time hand tracking in trauma surgery is essential for supporting rapid and precise intraoperative decisions. We propose a YOLOv10-based framework...
arXiv:2602.18960v1 Announce Type: new Abstract: The remarkable performance of modern AI systems has been driven by unprecedented scales of data, computation, and energy -- far...
arXiv:2602.18961v1 Announce Type: new Abstract: This paper presents a depth-enhanced YOLO-SAM2 framework for detecting ballast insufficiency in railway tracks using RGB-D data. Although YOLOv8 provides...
arXiv:2602.18962v1 Announce Type: new Abstract: The double empathy problem frames communication difficulties between neurodivergent and neurotypical individuals as arising from mutual misunderstanding, yet most interventions...
arXiv:2602.18964v1 Announce Type: new Abstract: Sarcasm detection poses a fundamental challenge in computational semantics, requiring models to resolve disparities between literal and intended meaning. The...