Show newer

A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents arxiv.org/abs/2603.25761 .CV .DL

CANGuard: A Spatio-Temporal CNN-GRU-Attention Hybrid Architecture for Intrusion Detection in In-Vehicle CAN Networks arxiv.org/abs/2603.25763 .CR .AI

Consistency Amplifies: How Behavioral Variance Shapes Agent Accuracy arxiv.org/abs/2603.25764 .SE .AI

Evaluating Synthetic Images as Effective Substitutes for Experimental Data in Surface Roughness Classification arxiv.org/abs/2603.25765 -mat.mtrl-sci .CV

ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models arxiv.org/abs/2603.25766 .RO .AI

Model2Kernel: Model-Aware Symbolic Execution For Safe CUDA Kernels arxiv.org/abs/2603.24595 .PL .AI

Algorithmic Barriers to Detecting and Repairing Structural Overspecification in Adaptive Data-Structure Selection arxiv.org/abs/2603.24597 .CC

Photoacoustic tomography with time-dependent damping: Theoretical and a convolutional neural network-guided numerical inversion procedure arxiv.org/abs/2603.24610 .NA -ph .MP .NA

Causal AI For AMS Circuit Design: Interpretable Parameter Effects Analysis arxiv.org/abs/2603.24618 .AR .AI .LG

Scalable Air-to-Ground Wireless Channel Modeling Using Environmental Context and Generative Diffusion arxiv.org/abs/2603.24620 .SP .NI

ReSyn: A Generalized Recursive Regular Expression Synthesis Framework arxiv.org/abs/2603.24624 .PL .SE

Optimal Unlabeled Pebble Motion on Trees and its Application to Multi-Agent Path Finding arxiv.org/abs/2603.23503 .DS

The HyperFrog Cryptosystem: High-Genus Voxel Topology as a Trapdoor for Post-Quantum KEMs arxiv.org/abs/2603.23505 -ph .CR

Leveraging Computerized Adaptive Testing for Cost-effective Evaluation of Large Language Models in Medical Benchmarking arxiv.org/abs/2603.23506 .CL .AI

Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes arxiv.org/abs/2603.23507 .CL .AI .LG

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.