Stay updated with the latest research and technology news
arXiv:2504.09587v4 Announce Type: replace Abstract: Language-goal aerial navigation requires UAVs to localize targets in the complex outdoors, such as urban blocks based on textual instructions....
arXiv:2504.10212v3 Announce Type: replace Abstract: The identification of Partial Differential Equations (PDEs) has emerged as a prominent data-driven approach for mathematical modeling and has attracted...
arXiv:2504.18274v3 Announce Type: replace Abstract: We develop a linear response framework for interpretability that treats a neural network as a Bayesian statistical mechanical system. A...
arXiv:2504.18317v5 Announce Type: replace Abstract: Achieving precise visual localization in GPS-limited urban environments poses significant challenges for resource-constrained mobile platforms, particularly under strict bandwidth, memory,...
arXiv:2504.19577v2 Announce Type: replace Abstract: Robotic automation is a key technology that increases the efficiency and flexibility of manufacturing processes. However, one of the challenges...
arXiv:2504.19678v2 Announce Type: replace Abstract: Large language models and autonomous AI agents have evolved rapidly, resulting in a diverse array of evaluation benchmarks, frameworks, and...
arXiv:2504.21052v2 Announce Type: replace Abstract: Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a...
arXiv:2505.00400v2 Announce Type: replace Abstract: Modular robots have the potential to revolutionize automation, as one can optimize their composition for any given task. However, finding...
arXiv:2505.00940v3 Announce Type: replace Abstract: When synthesizing multi-source high-dimensional data, a key objective is to extract low-dimensional representations that effectively approximate the original features across...
arXiv:2505.01566v3 Announce Type: replace Abstract: This paper proposes a coordinated routing approach that investigates the use of connected and automated vehicles (CAVs) in dedicated bus...
arXiv:2505.02428v2 Announce Type: replace Abstract: The growing demand for accessible mental health support requires training more counselors, yet existing approaches remain resource-intensive and difficult to...
arXiv:2505.04095v2 Announce Type: replace Abstract: Accurate localization is crucial for water robotics, yet traditional onboard Global Navigation Satellite System (GNSS) approaches are difficult or ineffective...
arXiv:2505.05286v3 Announce Type: replace Abstract: Recent advances in agentic large language models (LLMs) have substantially improved Text-to-SQL, enabling users without database expertise to query databases...
arXiv:2505.06046v4 Announce Type: replace Abstract: As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for...
arXiv:2505.06746v2 Announce Type: replace Abstract: We introduce M$^3$CAD, a comprehensive benchmark designed to advance research in generic cooperative autonomous driving. M$^3$CAD comprises 204 sequences with...
arXiv:2505.07365v2 Announce Type: replace Abstract: We present Task 5 of the DCASE 2025 Challenge: an Audio Question Answering (AQA) benchmark spanning multiple domains of sound...
arXiv:2505.09109v5 Announce Type: replace Abstract: Due to the deformability of garments, generating a large amount of high-quality data for robotic garment manipulation tasks is highly...
arXiv:2505.09889v2 Announce Type: replace Abstract: Shared autonomy in driving requires anticipating human behavior, flagging risk before it becomes unavoidable, and transferring control safely and smoothly....
arXiv:2505.10068v2 Announce Type: replace Abstract: In this work, we study the componentwise (Schur) product of monomial-Cartesian codes by exploiting its correspondence with the Minkowski sum...
arXiv:2505.10238v5 Announce Type: replace Abstract: Character image animation has rapidly advanced with the rise of digital humans. However, existing methods rely largely on 2D-rendered pose...
arXiv:2505.10742v3 Announce Type: replace Abstract: Systems like ChatGPT and Claude assist billions through proactive dialogue-offering unsolicited, task-relevant information. Drawing on Cognitive Load Theory, we study...
arXiv:2505.10822v2 Announce Type: replace Abstract: Knowledge distillation compresses a larger neural model (teacher) into smaller, faster student models by training them to match teacher outputs....
arXiv:2505.10845v2 Announce Type: replace Abstract: Machine unlearning is the process of removing the imprint left by specific data samples during the training of a machine...
arXiv:2505.11709v3 Announce Type: replace Abstract: Imitation learning for manipulation has a well-known data scarcity problem. Unlike natural language and 2D computer vision, there is no...