Stay updated with the latest research and technology news
arXiv:2602.18833v1 Announce Type: new Abstract: Convolutional neural networks have remarkably progressed the performance of distinguishing plant diseases, severity grading, and nutrition deficiency prediction using leaf...
arXiv:2602.18834v1 Announce Type: new Abstract: In blockchain applications, transaction confirmation is often treated as usability friction to be minimized or removed. However, confirmation also marks...
arXiv:2602.18835v1 Announce Type: new Abstract: Food waste management is critical for sustainability, yet inorganic contaminants hinder recycling potential. Robotic automation presents a compelling approach to...
arXiv:2602.18837v1 Announce Type: new Abstract: Despite their theoretical advantages, spectral methods based on the graph Fourier transform (GFT) are seldom used in graph neural networks...
arXiv:2602.18842v1 Announce Type: new Abstract: The proliferation of highly realistic AI-generated images poses critical challenges for digital forensics, demanding precise pixel-level localization of manipulated regions....
arXiv:2602.18843v1 Announce Type: new Abstract: We introduce ABD, a benchmark for default-exception abduction over finite first-order worlds. Given a background theory with an abnormality predicate...
arXiv:2602.18844v1 Announce Type: new Abstract: Dependently-typed proof assistants furnish expressive foundations for mechanised mathematics and verified software. However, automation for these systems has been either...
arXiv:2602.18845v1 Announce Type: new Abstract: With the rapid deployment and widespread adoption of multimodal large language models (MLLMs), disputes regarding model version attribution and ownership...
arXiv:2602.18846v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization....
arXiv:2602.18849v1 Announce Type: new Abstract: Despite powering modern AI, transformers remain mysteriously brittle to train. We develop a stability theory that explains why pre-LayerNorm works,...
arXiv:2602.18850v1 Announce Type: new Abstract: Although in the literature it is common to find predictors and inference systems that try to predict human intentions, the...
arXiv:2602.18851v1 Announce Type: new Abstract: Attention scores in transformers are bilinear forms $S_{ij} = x_i^\top M x_j / \sqrt{d_h}$ whose maximum magnitude governs overflow risk...
arXiv:2602.18853v1 Announce Type: new Abstract: Domain Generalization in Semantic Segmentation (DG-SS) aims to enable segmentation models to perform robustly in unseen environments. However, conventional DG-SS...
arXiv:2602.18856v1 Announce Type: new Abstract: Reinforcement learning (RL) has enabled major advances in fields such as robotics and natural language processing. A key challenge in...
arXiv:2602.18857v1 Announce Type: new Abstract: Optimally trading-off exploration and exploitation is the holy grail of reinforcement learning as it promises maximal data-efficiency for solving any...
arXiv:2602.18858v1 Announce Type: new Abstract: Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage...
arXiv:2602.18861v1 Announce Type: new Abstract: We present a framework for end-to-end joint quantization of Vision Transformers trained on ImageNet for the purpose of image classification....
arXiv:2602.18862v1 Announce Type: new Abstract: Unilateral muscle weakness often leads to asymmetric gait, disrupting interlimb coordination and stance timing. This study presents a reinforcement learning...
arXiv:2602.18866v1 Announce Type: new Abstract: Despite the widespread use of boosting in structured prediction, a general theoretical understanding of aggregation beyond scalar losses remains incomplete....
arXiv:2602.18867v1 Announce Type: new Abstract: Active Learning (AL) reduces annotation costs in medical imaging by selecting only the most informative samples for labeling, but suffers...
arXiv:2602.18869v1 Announce Type: new Abstract: Semantic segmentation of 3D LiDAR point clouds is important in urban remote sensing for understanding real-world street environments. This task,...
arXiv:2602.18872v1 Announce Type: new Abstract: We introduce a pignistic-transform-based methodology for fair comparison of Bayesian log-odds and Dempster's combination rule in occupancy grid mapping, matching...
arXiv:2602.18873v1 Announce Type: new Abstract: Text-guided dynamic 3D character generation has advanced rapidly, yet producing high-quality motion that faithfully reflects rich textual descriptions remains challenging....
arXiv:2602.18874v1 Announce Type: new Abstract: Few-shot Chinese font generation aims to synthesize new characters in a target style using only a handful of reference images....