Stay updated with the latest research and technology news
arXiv:2601.17069v1 Announce Type: new Abstract: Centralized training with decentralized execution (CTDE) has been the dominant paradigm in multi-agent reinforcement learning (MARL), but its reliance on...
arXiv:2601.17071v1 Announce Type: new Abstract: We present an efficient method for image segmentation in the presence of strong inhomogeneities. The approach can be interpreted as...
arXiv:2601.17072v1 Announce Type: new Abstract: Almost every industry today confronts the potential role of artificial intelligence and machine learning in its future. While many studies...
arXiv:2601.17073v1 Announce Type: new Abstract: Brain organization is increasingly characterized through multiple imaging modalities, most notably structural connectivity (SC) and functional connectivity (FC). Integrating these...
arXiv:2601.17074v1 Announce Type: new Abstract: The accurate estimation of Arctic snow depth ($h_s$) remains a critical time-varying inverse problem due to the extreme scarcity and...
arXiv:2601.17076v1 Announce Type: new Abstract: Multi-view multi-label classification (MvMLC) is indispensable for modern web applications aggregating information from diverse sources. However, real-world web-scale settings are...
arXiv:2601.17077v1 Announce Type: new Abstract: The problem of finding the general classification of geodetic graphs is still open. We believe that one of the obstacles...
arXiv:2601.17078v1 Announce Type: new Abstract: We give two natural definitions of polynomial-time computability for L2 functions; and we show them incomparable (unless complexity class FP_1...
arXiv:2601.17082v1 Announce Type: new Abstract: Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments are...
arXiv:2601.17086v1 Announce Type: new Abstract: Neural text-to-speech (TTS) systems systematically mispronounce low-resource proper nouns, particularly non-English names, brands, and geographic locations, due to their underrepresentation...
arXiv:2601.17087v1 Announce Type: new Abstract: Agentic benchmarks increasingly rely on LLM-simulated users to scalably evaluate agent performance, yet the robustness, validity, and fairness of this...
arXiv:2601.17088v1 Announce Type: new Abstract: Virtual try-on systems allow users to interactively try different products within VR scenarios. However, most existing VTON methods operate only...
arXiv:2601.17089v1 Announce Type: new Abstract: In recent years, Multimodal Large Language Models (MLLMs) have made significant progress in visual question answering tasks. However, directly applying...
arXiv:2601.17090v1 Announce Type: new Abstract: Partial differential equations (PDEs) govern complex systems, yet neural operators often struggle to efficiently capture the long-range, nonlocal interactions inherent...
arXiv:2601.17091v1 Announce Type: new Abstract: ROCKET (RandOm Convolutional KErnel Transform) is a feature extraction algorithm created for Time Series Classification (TSC), published in 2019. It...
arXiv:2601.17093v1 Announce Type: new Abstract: Comparing neural network representations is essential for understanding and validating models in scientific applications. Existing methods, however, often provide a...
arXiv:2601.17094v1 Announce Type: new Abstract: Large Language Models (LLMs) generate fluent text, yet whether they truly understand the world or merely produce plausible language about...
arXiv:2601.17095v1 Announce Type: new Abstract: For architectural design, representation across multiple Levels of Details (LoD) is essential for achieving a smooth transition from conceptual massing...
arXiv:2601.17096v1 Announce Type: new Abstract: Recent scholarship typically characterizes Large Language Models (LLMs) through either an \textit{Instrumental Paradigm} (viewing models as reflections of their developers'...
arXiv:2601.17097v1 Announce Type: new Abstract: Real-time automatic speech recognition systems are increasingly integrated into interactive applications, from voice assistants to live transcription services. However, scaling...
arXiv:2601.17107v1 Announce Type: new Abstract: Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant...
arXiv:2601.17108v1 Announce Type: new Abstract: This paper proposes a Mamba-assisted neural network framework incorporating self-attention mechanism to achieve improved channel estimation with low complexity for...
arXiv:2601.17110v1 Announce Type: new Abstract: Accurate short-term energy consumption forecasting is essential for efficient power grid management, resource allocation, and market stability. Traditional time-series models...
arXiv:2601.17111v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are typically pre-trained with explicit load-balancing constraints to ensure statistically balanced expert routing. Despite this, we observe...