Stay updated with the latest research and technology news
arXiv:2601.18189v1 Announce Type: new Abstract: Continuous optimization has significantly advanced causal discovery, yet existing methods (e.g., NOTEARS) generally guarantee only asymptotic convergence to a stationary...
arXiv:2601.18190v1 Announce Type: new Abstract: Vision-Language Pre-training (VLP) models like CLIP have significantly advanced Remote Sensing Image-Text Retrieval (RSITR). However, existing methods predominantly rely on...
arXiv:2601.18192v2 Announce Type: new Abstract: Reconstructing human dynamic visual perception from electroencephalography (EEG) signals is of great research significance since EEG's non-invasiveness and high temporal...
arXiv:2601.18193v1 Announce Type: new Abstract: Visual designers often seek inspiration from Chinese paintings when tasked with creating Chinese-style illustrations, posters, etc. Our formative study (N=10)...
arXiv:2601.18195v1 Announce Type: new Abstract: Visual quality assessment (VQA) is increasingly shifting from scalar score prediction toward interpretable quality understanding -- a paradigm that demands...
arXiv:2601.18197v1 Announce Type: new Abstract: While Large Vision-Language Models (LVLMs) have significantly advanced GUI agents' capabilities in parsing textual instructions, interpreting screen content, and executing...
arXiv:2601.18198v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are eminently suitable for wireless resource management, thanks to their scalability, but they still face computational...
arXiv:2601.18200v1 Announce Type: new Abstract: Wireless foundation models promise transformative capabilities for channel state information (CSI) processing across diverse 6G network applications, yet face fundamental...
arXiv:2601.18202v1 Announce Type: new Abstract: Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking...
arXiv:2601.18203v2 Announce Type: new Abstract: Existing multimodal document question-answering (QA) systems predominantly rely on flat semantic retrieval, representing documents as a set of disconnected text...
arXiv:2601.18204v1 Announce Type: new Abstract: Large language model-based agents operating in long-horizon interactions require memory systems that support temporal consistency, multi-hop reasoning, and evidence-grounded reuse...
arXiv:2601.18207v1 Announce Type: new Abstract: Search agents are language models (LMs) that reason and search knowledge bases (or the web) to answer questions; recent methods...
arXiv:2601.18213v1 Announce Type: new Abstract: Modeling long-term user behavior trajectories is essential for understanding evolving preferences and enabling proactive recommendations. However, most sequential recommenders focus...
arXiv:2601.18216v1 Announce Type: new Abstract: Ransomware variants increasingly combine privilege escalation with sophisticated evasion strategies such as intermittent encryption, low-entropy encryption, and imitation attacks. Such...
arXiv:2601.18217v1 Announce Type: new Abstract: Generalist LLM agents are often post-trained on a narrow set of environments but deployed across far broader, unseen domains. In...
arXiv:2601.18218v1 Announce Type: new Abstract: The dissemination of scholarly research is critical, yet researchers often lack the time and skills to create engaging content for...
arXiv:2601.18220v1 Announce Type: new Abstract: Forced alignment (FA) predicts start and end timestamps for words or characters in speech, but existing methods are language-specific and...
arXiv:2601.18222v1 Announce Type: new Abstract: Deep homography estimation has broad applications in computer vision and robotics. Remarkable progresses have been achieved while the existing methods...
arXiv:2601.18224v1 Announce Type: new Abstract: We study the generalized conditional gradient (GCG) method for time-dependent second-order mean field games (MFG) with local coupling terms. While...
arXiv:2601.18225v1 Announce Type: new Abstract: Large language model (LLM)-based agents are increasingly deployed in e-commerce shopping. To perform thorough, user-tailored product searches, agents should interpret...
arXiv:2601.18226v1 Announce Type: new Abstract: Conventional agent systems often struggle in open-ended environments where task distributions continuously drift and external supervision is scarce. Their reliance...
arXiv:2601.18228v1 Announce Type: new Abstract: Detection of human emotions based on facial images in real-world scenarios is a difficult task due to low image quality,...
arXiv:2601.18230v1 Announce Type: new Abstract: This chapter examines the evolution of library services at the University of Li\`ege (ULi\`ege), with a focus on the implementation...
arXiv:2601.18231v1 Announce Type: new Abstract: Adapting pre-trained models to unseen feature modalities has become increasingly important due to the growing need for cross-disciplinary knowledge integration.~A...