Stay updated with the latest research and technology news
arXiv:2603.01718v1 Announce Type: new Abstract: Large language models (LLMs) have diffused rapidly into academic writing since late 2022. Using the complete population of 109,393 research...
arXiv:2603.01720v1 Announce Type: new Abstract: In laparoscopic liver surgery, augmented reality technology enhances intraoperative anatomical guidance by overlaying 3D liver models from preoperative CT/MRI onto...
arXiv:2603.01724v1 Announce Type: new Abstract: Online content moderation is essential for maintaining a healthy digital environment, and reliance on AI for this task continues to...
arXiv:2603.01725v1 Announce Type: new Abstract: Recently, significant breakthroughs have been made in all-in-one image restoration (AiOIR), which can handle multiple restoration tasks with a single...
arXiv:2603.01729v1 Announce Type: new Abstract: We propose a multi-patient inverse modeling framework for identifying effective calcium and citrate diffusion coefficients in hollow-fiber hemodialysis devices. The...
arXiv:2603.01730v1 Announce Type: new Abstract: Decentralized federated learning (DFL) has emerged as a transformative server-free paradigm that enables collaborative learning over large-scale heterogeneous networks. However,...
arXiv:2603.01731v1 Announce Type: new Abstract: Many physical and engineering systems require solving direct problems to predict behavior and inverse problems to determine unknown parameters from...
arXiv:2603.01732v1 Announce Type: new Abstract: Embedding models are crucial to modern NLP. However, the creation of the most effective models relies on carefully constructed supervised...
arXiv:2603.01736v1 Announce Type: new Abstract: We study the universal attainability of the expurgated error exponent for discrete memoryless channels (DMCs). While the random-coding exponent is...
arXiv:2603.01739v1 Announce Type: new Abstract: Federated Learning (FL) faces major challenges in real-world deployments due to statistical heterogeneity across clients and system heterogeneity arising from...
arXiv:2603.01741v1 Announce Type: new Abstract: Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy....
arXiv:2603.01743v1 Announce Type: new Abstract: Anticipating future actions in videos is challenging, as the observed frames provide only evidence of past activities, requiring the inference...
arXiv:2603.01746v1 Announce Type: new Abstract: Most information in our world is organized hierarchically; however, many Deep Learning approaches do not leverage this semantically rich structure....
arXiv:2603.01748v1 Announce Type: new Abstract: World models aim to capture the states and dynamics of an environment in a compact latent space. Moreover, using Boolean...
arXiv:2603.01749v1 Announce Type: new Abstract: We consider the problem of type estimation over unsourced multiple access fading channels in distributed multiple-input multiple-output (D-MIMO) systems. Unlike...
arXiv:2603.01750v1 Announce Type: new Abstract: Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making...
arXiv:2603.01751v1 Announce Type: new Abstract: Continuum robots possess high flexibility and redundancy, making them well suited for safe interaction in complex environments, yet their continuous...
arXiv:2603.01752v1 Announce Type: new Abstract: Motivation: Sparse autoencoders (SAEs) decompose foundation model activations into interpretable features, but causal feature-to-feature interactions across network depth remain unknown...
arXiv:2603.01755v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) presents a promising pathway toward realizing autonomous and self-improving wireless network services. However, resource-constrained, widely distributed,...
arXiv:2603.01756v1 Announce Type: new Abstract: Automatic generation of radiology reports seeks to reduce clinician workload while improving documentation consistency. Existing methods that adopt encoder-decoder or...
arXiv:2603.01757v1 Announce Type: new Abstract: Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high...
arXiv:2603.01758v1 Announce Type: new Abstract: Heterogeneous multi-modal remote sensing object detection aims to accurately detect objects from diverse sensors (e.g., RGB, SAR, Infrared). Existing approaches...
arXiv:2603.01759v1 Announce Type: new Abstract: Training large foundation models from scratch for domain-specific applications is almost impossible due to data limits and long-tailed distributions --...
arXiv:2603.01762v1 Announce Type: new Abstract: Spatiotemporal partial differential equations (PDEs) underpin a wide range of scientific and engineering applications. Neural PDE solvers offer a promising...