Stay updated with the latest research and technology news
arXiv:2602.18022v2 Announce Type: replace Abstract: Training-free control over editing intensity is a critical requirement for diffusion-based image editing models built on the Diffusion Transformer (DiT)...
arXiv:2602.18292v2 Announce Type: replace Abstract: Decoding sits between a language model and everything we do with it, yet it is still treated as a heuristic...
arXiv:2602.18467v2 Announce Type: replace Abstract: This study explores the relationship between body composition metrics, self-compassion, and social support among college students. Using seasonal body composition...
arXiv:2602.18671v2 Announce Type: replace Abstract: We reinterpret the final Large Language Model (LLM) softmax classifier as an Energy-Based Model (EBM), decomposing the sequence-to-sequence probability chain...
arXiv:2602.18676v2 Announce Type: replace Abstract: Hybrid meetings often begin with social awkwardness and asymmetric participation, particularly for remote attendees who lack access to informal, co-present...
arXiv:2602.18755v2 Announce Type: replace Abstract: Prefill/decode disaggregation is increasingly adopted in LLM serving to improve the latency-throughput tradeoff and meet strict TTFT and TPOT SLOs....
arXiv:2602.18788v2 Announce Type: replace Abstract: We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP...
arXiv:2602.18858v2 Announce Type: replace Abstract: Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage...
arXiv:2602.19206v2 Announce Type: replace Abstract: Zero-shot 3D Anomaly Detection is an emerging task that aims to detect anomalies in a target dataset without any target...
arXiv:2602.19430v2 Announce Type: replace Abstract: Despite the inherent advantages of thermal infrared(TIR) imaging, large-scale data collection and annotation remain a major bottleneck for TIR-based perception....
arXiv:2602.19439v2 Announce Type: replace Abstract: Supply chain optimization models frequently become infeasible because of modeling errors. Diagnosis and repair require scarce OR expertise: analysts must...
arXiv:2602.19674v2 Announce Type: replace Abstract: Remote monitoring of heart failure (HF) via speech signals provides a non-invasive and cost-effective solution for long-term patient management. However,...
arXiv:2602.19760v2 Announce Type: replace Abstract: The classical notion of extreme $L_p$ discrepancy is a quantitative measure for the irregularity of distribution of finite point sets...
arXiv:2602.19784v2 Announce Type: replace Abstract: The Low-Altitude Economy (LAE) is rapidly emerging as a new technological and industrial frontier, with unmanned aerial vehicles (UAVs), electric...
arXiv:2602.19878v2 Announce Type: replace Abstract: Every ODRL 2.2 constraint compares a single scalar value: (leftOperand, operator, rightOperand). Five of ODRL's left operands, however, denote multi-dimensional...
arXiv:2602.19983v2 Announce Type: replace Abstract: Robots are increasingly operating in open-world environments where safe behavior depends on context: the same hallway may require different navigation...
arXiv:2602.20070v2 Announce Type: replace Abstract: We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear systems....
arXiv:2602.20083v2 Announce Type: replace Abstract: Deploying Retrieval-Augmented Generation (RAG) on edge devices is in high demand, but is hindered by the latency of massive data...
arXiv:2602.20156v3 Announce Type: replace Abstract: LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users...
arXiv:2602.20205v2 Announce Type: replace Abstract: Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens....
arXiv:2602.20223v2 Announce Type: replace Abstract: Recently, TabPFN has gained attention as a foundation model for tabular data. However, it struggles to integrate heterogeneous modalities such...
arXiv:2602.20292v2 Announce Type: replace Abstract: Agentic AI systems are deployed with expectations of substantial productivity gains, yet rigorous empirical evidence reveals systematic discrepancies between pre-deployment...
arXiv:2602.20309v2 Announce Type: replace Abstract: Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to...
arXiv:2602.20541v2 Announce Type: replace Abstract: We study the problem of fairly allocating indivisible goods when limited sharing is allowed, that is, each good may be...