Stay updated with the latest research and technology news
arXiv:2602.19719v1 Announce Type: new Abstract: Existing methods for instance-level 6D pose estimation typically rely on neural networks that either directly regress the pose in $\mathrm{SE}(3)$...
arXiv:2602.19720v1 Announce Type: new Abstract: Multi-die FPGAs enable device scaling beyond reticle limits but introduce severe interconnect overhead across die boundaries. Inter-die connections, commonly referred...
arXiv:2602.19723v1 Announce Type: new Abstract: Synthesizing missing modalities in multi-modal magnetic resonance imaging (MRI) is vital for ensuring diagnostic completeness, particularly when full acquisitions are...
arXiv:2602.19728v1 Announce Type: new Abstract: Sequential recommender systems aim to predict a user's future interests by extracting temporal patterns from their behavioral history. Existing approaches...
arXiv:2602.19733v1 Announce Type: new Abstract: Algorithm unrolling is ubiquitous in machine learning, particularly in hyperparameter optimization and meta-learning, where Jacobians of solution mappings are computed...
arXiv:2602.19735v1 Announce Type: new Abstract: In autonomous driving, robust place recognition is critical for global localization and loop closure detection. While inter-modality fusion of camera...
arXiv:2602.19736v1 Announce Type: new Abstract: Image Super-Resolution (SR) aims to recover high-resolution (HR) details from low-resolution (LR) inputs, a task where Denoising Diffusion Probabilistic Models...
arXiv:2602.19742v1 Announce Type: new Abstract: Wildfire monitoring demands timely data collection and processing for early detection and rapid response. UAV-assisted edge computing is a promising...
arXiv:2602.19743v1 Announce Type: new Abstract: This paper explores how natural-language descriptions of formal languages can be compared to their formal representations and how semantic differences...
arXiv:2602.19745v1 Announce Type: new Abstract: BioFabrics were introduced by Longabaugh in 2012 as a way to draw large graphs in a clear and uncluttered manner....
arXiv:2602.19753v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a leading technology for high-quality 3D scene reconstruction. However, the iterative refinement and...
arXiv:2602.19754v1 Announce Type: new Abstract: From a small community of pioneering artists who experimented with artificial intelligence (AI) in the 1970s, AI art has expanded,...
arXiv:2602.19756v1 Announce Type: new Abstract: Recent advances in multimodal learning have achieved remarkable success across diverse vision-language tasks. However, such progress heavily relies on large-scale...
arXiv:2602.19758v1 Announce Type: new Abstract: Open Radio Access Network (RAN) was designed with native Artificial Intelligence (AI) as a core pillar, enabling AI- driven xApps...
arXiv:2602.19760v1 Announce Type: new Abstract: The classical notion of extreme $L_p$ discrepancy is a quantitative measure for the irregularity of distribution of finite point sets...
arXiv:2602.19763v1 Announce Type: new Abstract: Autonomous drone-based tree pruning needs accurate, real-time depth estimation from stereo cameras. Depth is computed from disparity maps using $Z...
arXiv:2602.19764v1 Announce Type: new Abstract: Realizing dexterous embodied manipulation necessitates the deep integration of heterogeneous multimodal sensory inputs. However, current vision-centric paradigms often overlook the...
arXiv:2602.19766v1 Announce Type: new Abstract: Generating explorable 3D scenes from a single image is a highly challenging problem in 3D vision. Existing methods struggle to...
arXiv:2602.19768v1 Announce Type: new Abstract: Recent Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in image understanding and natural language generation. However, current approaches focus predominantly...
arXiv:2602.19769v1 Announce Type: new Abstract: Contemporary AI art's diverse and widely recognized repertoire features numerous artworks that share conceptual, thematic, narrative, procedural, or presentational properties...
arXiv:2602.19770v1 Announce Type: new Abstract: Explainable artificial intelligence has emerged as a promising field of research to address reliability concerns in artificial intelligence. Despite significant...
arXiv:2602.19776v1 Announce Type: new Abstract: We develop layered monoidal theories -- a generalisation of monoidal theories combining formal descriptions of a system at different levels...
arXiv:2602.19777v1 Announce Type: new Abstract: The increasing adoption of System-on-Chip Field-Programmable Gate Arrays (SoC FPGAs) in AI-enabled satellite systems, valued for their reconfigurability and in-orbit...
arXiv:2602.19778v1 Announce Type: new Abstract: Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire....