Stay updated with the latest research and technology news
arXiv:2602.02057v1 Announce Type: new Abstract: Vector databases have become a cornerstone of modern information retrieval, powering applications in recommendation, search, and retrieval-augmented generation (RAG) pipelines....
arXiv:2602.02060v1 Announce Type: new Abstract: Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains poorly understood how their predictions depend on specific internal...
arXiv:2602.02061v1 Announce Type: new Abstract: Explosive demands for LLMs often cause user queries to accumulate in server queues, requiring efficient routing (query-LLM matching) and scheduling...
arXiv:2602.02063v1 Announce Type: new Abstract: Automated vehicles lack natural communication channels with other road users, making external Human-Machine Interfaces (eHMIs) essential for conveying intent and...
arXiv:2602.02066v1 Announce Type: new Abstract: We consider approximation or recovery of functions based on a finite number of function evaluations. This is a well-studied problem...
arXiv:2602.02067v1 Announce Type: new Abstract: Coronary artery stenosis is a leading cause of cardiovascular disease, diagnosed by analyzing the coronary arteries from multiple angiography views....
arXiv:2602.02068v1 Announce Type: new Abstract: The present work addresses the Cauchy problem for an abstract nonlinear system of coupled hyperbolic equations associated with the Timoshenko...
arXiv:2602.02071v1 Announce Type: new Abstract: As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference....
arXiv:2602.02072v1 Announce Type: new Abstract: The adaptive smoothing method (ASM) is a widely used approach for traffic state reconstruction. This article presents a Python implementation...
arXiv:2602.02079v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable of generating functional source code, raising concerns about authorship, accountability, and security. While...
arXiv:2602.02080v1 Announce Type: new Abstract: We study learning under a two-step contrastive example oracle, as introduced by Mansouri et. al. (2025), where each queried (or...
arXiv:2602.02081v1 Announce Type: new Abstract: Learning from positive and unlabeled data (PU learning) is a weakly supervised variant of binary classification in which the learner...
arXiv:2602.02084v1 Announce Type: new Abstract: Current repository agents encounter a reasoning disconnect due to fragmented representations, as existing methods rely on isolated API documentation or...
arXiv:2602.02087v1 Announce Type: new Abstract: This paper addresses the problem of designing efficient no-swap regret algorithms for combinatorial bandits, where the number of actions $N$...
arXiv:2602.02089v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) enables high-quality, real-time rendering for bounded scenes, its extension to large-scale urban environments gives rise...
arXiv:2602.02090v1 Announce Type: new Abstract: Constructing domain-specific knowledge graphs from unstructured text remains challenging due to heterogeneous entity mentions, long-tail relation distributions, and the absence...
arXiv:2602.02091v1 Announce Type: new Abstract: Higher-order beta-matching is the following decision problem: given two simply typed lambda-terms, can the first term be instantiated to be...
arXiv:2602.02092v1 Announce Type: new Abstract: We introduce FSVideo, a fast speed transformer-based image-to-video (I2V) diffusion framework. We build our framework on the following key components:...
arXiv:2602.02093v1 Announce Type: new Abstract: Single-cell foundation models learn by reconstructing masked gene expression, implicitly treating technical noise as signal. With dropout rates exceeding 90%,...
arXiv:2602.02095v1 Announce Type: new Abstract: We review some recent advances in the field of element-based algebraic stabilization for continuous finite element discretizations of nonlinear hyperbolic...
arXiv:2602.02098v1 Announce Type: new Abstract: Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches...
arXiv:2602.02099v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) can elicit strong multi-step reasoning, yet it often encourages overly verbose traces. Moreover, naive...
arXiv:2602.02100v1 Announce Type: new Abstract: The growth of Generative Artificial Intelligence (GenAI) has shifted disinformation production from manual fabrication to automated, large-scale manipulation. This article...
arXiv:2602.02103v1 Announce Type: new Abstract: This work stems from prior complementary observations on the dynamics of Chain-of-Thought (CoT): Large Language Models (LLMs) is shown latent...