Stay updated with the latest research and technology news
arXiv:2602.13958v1 Announce Type: new Abstract: Language models are widely used in chemistry for molecular property prediction and small-molecule generation, yet Natural Products (NPs) remain underexplored...
arXiv:2602.13960v1 Announce Type: new Abstract: Constant-stepsize stochastic approximation (SA) is widely used in learning for computational efficiency. For a fixed stepsize, the iterates typically admit...
arXiv:2602.13961v1 Announce Type: new Abstract: Data-driven approaches like deep learning are rapidly advancing planetary science, particularly in Mars exploration. Despite recent progress, most existing benchmarks...
arXiv:2602.13962v1 Announce Type: new Abstract: In modern software development, developers frequently need to understand code behavior at a glance -- whether reviewing pull requests, debugging...
arXiv:2602.13967v1 Announce Type: new Abstract: Most evaluations of External Memory Module assume a static setting: memory is built offline and queried at a fixed state....
arXiv:2602.13971v1 Announce Type: new Abstract: Recommendation systems are essential for personalizing e-commerce shopping experiences. Among these, Trigger-Induced Recommendation (TIR) has emerged as a key scenario,...
arXiv:2602.13977v1 Announce Type: new Abstract: Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision-Language-Action (VLA) models, but its requirement for massive real-world...
arXiv:2602.13979v1 Announce Type: new Abstract: Alzheimer's disease (AD) has become a prevalent neurodegenerative disease worldwide. Traditional diagnosis still relies heavily on medical imaging and clinical...
arXiv:2602.13980v1 Announce Type: new Abstract: Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly...
arXiv:2602.13981v1 Announce Type: new Abstract: In the {\sc Vertex Multicut} problem the input consists of a graph $G$, integer $k$, and a set $\mathbf{T} =...
arXiv:2602.13985v1 Announce Type: new Abstract: Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of human...
arXiv:2602.13987v1 Announce Type: new Abstract: The unit testing of Deep Learning (DL) libraries is challenging due to complex numerical semantics and implicit tensor constraints. Traditional...
arXiv:2602.13989v1 Announce Type: new Abstract: Current online safety technologies overly rely on parental mediation and often fail to address the unique challenges faced by youth...
arXiv:2602.13993v1 Announce Type: new Abstract: Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive. Previous acceleration methods, such as pruning and...
arXiv:2602.13994v1 Announce Type: new Abstract: Personalized text-to-image generation aims to integrate specific identities into arbitrary contexts. However, existing tuning-free methods typically employ Spatially Uniform Visual...
arXiv:2602.13998v1 Announce Type: new Abstract: Customer service has evolved beyond in-person visits and phone calls to include live chat, AI chatbots and social media, among...
arXiv:2602.13999v1 Announce Type: new Abstract: The prevailing paradigm in Robotic Mobile Fulfillment Systems (RMFS) typically treats order scheduling and multi-agent pathfinding as isolated sub-problems. We...
arXiv:2602.14002v1 Announce Type: new Abstract: Large Language Models increasingly rely on self-explanations, such as chain of thought reasoning, to improve performance on multi step question...
arXiv:2602.14003v1 Announce Type: new Abstract: The large artificial intelligence models (LAMs) show strong capabilities in perception, reasoning, and multi-modal understanding, and can enable advanced capabilities...
arXiv:2602.14009v1 Announce Type: new Abstract: Named Entity Recognition (NER) has emerged as a critical component in automating financial transaction processing, particularly in extracting structured information...
arXiv:2602.14011v1 Announce Type: new Abstract: Representing and predicting high-dimensional and spatiotemporally chaotic dynamical systems remains a fundamental challenge in dynamical systems and machine learning. Although...
arXiv:2602.14012v1 Announce Type: new Abstract: The integration of LLMs into vulnerability detection (VD) has shifted the field toward interpretable and context-aware analysis. While post-training methods...
arXiv:2602.14017v1 Announce Type: new Abstract: Subseasonal-to-seasonal (S2S) forecasts play an essential role in providing a decision-critical weeks-to-months planning window for climate resilience and sustainability, yet...
arXiv:2602.14021v1 Announce Type: new Abstract: Reconstructing and tracking dynamic 3D scenes remains a fundamental challenge in computer vision. Existing approaches often decouple geometry from motion:...