Stay updated with the latest research and technology news
arXiv:2601.20477v1 Announce Type: new Abstract: We study the supervised training dynamics of neural classifiers through the lens of binary hypothesis testing. We model classification as...
arXiv:2601.20478v1 Announce Type: new Abstract: Basso continuo is a baroque improvisatory accompaniment style which involves improvising multiple parts above a given bass line in a...
arXiv:2601.20480v1 Announce Type: new Abstract: High-dimensional neuroimaging data presents challenges for assessing neurodegenerative diseases due to complex non-linear relationships. Variational Autoencoders (VAEs) can encode scans...
arXiv:2601.20482v1 Announce Type: new Abstract: Column matching is a central task in reconciling schemas for data integration. Column names and descriptions are valuable for this...
arXiv:2601.20487v1 Announce Type: new Abstract: The introduction of artificial intelligence (AI) agents into human group settings raises essential questions about how these novel participants influence...
arXiv:2601.20494v1 Announce Type: new Abstract: We present a class of numerical schemes for two-dimensional systems of nonlocal conservation laws, which are based on utilizing well-known...
arXiv:2601.20499v1 Announce Type: new Abstract: The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In...
arXiv:2601.20503v1 Announce Type: new Abstract: White matter hyperintensities (WMH) and ischaemic stroke lesions (ISL) are imaging features associated with cerebral small vessel disease (SVD) that...
arXiv:2601.20504v1 Announce Type: new Abstract: Video generation models have achieved notable progress in static scenarios, yet their performance in motion video generation remains limited, with...
arXiv:2601.20507v1 Announce Type: new Abstract: Mobile devices rely on Trusted Execution Environments (TEEs) to execute security-critical code and protect sensitive assets. This security-critical code is...
arXiv:2601.20510v1 Announce Type: new Abstract: Recent advances in Text-to-Speech (TTS) systems have substantially increased the realism of synthetic speech, raising new challenges for audio deepfake...
arXiv:2601.20511v1 Announce Type: new Abstract: As social media platforms proliferate, users increasingly demand intuitive ways to create diverse, high-quality portrait collections. In this work, we...
arXiv:2601.20518v1 Announce Type: new Abstract: Topological deep learning has emerged for modeling higher-order relational structures beyond pairwise interactions that standard graph neural networks fail to...
arXiv:2601.20520v1 Announce Type: new Abstract: Recent diffusion-based Multimodal Large Language Models (dMLLMs) suffer from high inference latency and therefore rely on caching techniques to accelerate...
arXiv:2601.20524v1 Announce Type: new Abstract: Zero-shot anomaly detection aims to detect and localise abnormal regions in the image without access to any in-domain training images....
arXiv:2601.20526v1 Announce Type: new Abstract: Recently, adapting pre-trained models to downstream tasks has attracted increasing interest. Previous Parameter-Efficient-Tuning (PET) methods regard the pre-trained model as...
arXiv:2601.20529v1 Announce Type: new Abstract: Robotic prospecting for critical resources on the Moon, such as ilmenite, rare earth elements, and water ice, requires robust exploration...
arXiv:2601.20537v1 Announce Type: new Abstract: Markov-modulated fluid queues (MMFQs) are a powerful modeling framework for analyzing the performance of computer and communication systems. Their distinguishing...
arXiv:2601.20538v1 Announce Type: new Abstract: Large language model-powered multi-agent systems have emerged as powerful tools for simulating complex human-like systems. The interactions within these systems...
arXiv:2601.20539v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on...
arXiv:2601.20544v1 Announce Type: new Abstract: Data Visualization Literacy assessments are typically administered via fixed sets of Data Visualization items, despite substantial heterogeneity in how different...
arXiv:2601.20546v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in verbal creative tasks. However, previous assessments of the creative capabilities of LLMs...
arXiv:2601.20548v1 Announce Type: new Abstract: This paper critically examines the device identification process using machine learning, addressing common pitfalls in existing literature. We analyze the...
arXiv:2601.20552v1 Announce Type: new Abstract: We present DeepSeek-OCR 2 to investigate the feasibility of a novel encoder-DeepEncoder V2-capable of dynamically reordering visual tokens upon image...