Stay updated with the latest research and technology news
arXiv:2602.02615v1 Announce Type: new Abstract: Existing Byzantine robust aggregation mechanisms typically rely on fulldimensional gradi ent comparisons or pairwise distance computations, resulting in computational overhead...
arXiv:2602.02616v1 Announce Type: new Abstract: Simulating flow problems is at the core of many engineering applications but often requires high computational effort, especially when dealing...
arXiv:2602.02618v1 Announce Type: new Abstract: Learning behavioral taxonomies from animal-borne sensors is challenging because labels are scarce, classes are highly imbalanced, and behaviors may be...
arXiv:2602.02619v1 Announce Type: new Abstract: While Large Language Models (LLMs) excel at short-term tasks, scaling them to long-horizon agentic workflows remains challenging. The core bottleneck...
arXiv:2602.02623v1 Announce Type: new Abstract: Causal artificial intelligence aims to enhance explainability, trustworthiness, and robustness in AI by leveraging structural causal models (SCMs). In this...
arXiv:2602.02624v1 Announce Type: new Abstract: Studies on recommendations in social media have mainly analyzed the quality of recommended items (e.g., their diversity or biases) and...
arXiv:2602.02625v1 Announce Type: new Abstract: Agentic AI systems increasingly operate in shared social environments where they exchange information, instructions, and behavioral cues. However, little empirical...
arXiv:2602.02626v1 Announce Type: new Abstract: Adversarial training attains strong empirical robustness to specific adversarial attacks by training on concrete adversarial perturbations, but it produces neural...
arXiv:2602.02628v1 Announce Type: new Abstract: We introduce the competitive assignment problem, a two-player version of the well-known assignment problem. Given a set of tasks and...
arXiv:2602.02629v1 Announce Type: new Abstract: The digitization of healthcare has generated massive volumes of Electronic Health Records (EHRs), offering unprecedented opportunities for training Artificial Intelligence...
arXiv:2602.02630v1 Announce Type: new Abstract: This paper introduces TRAILDREAMS, a framework that uses a large language model (LLM) to automate the production of movie trailers....
arXiv:2602.02632v1 Announce Type: new Abstract: Large language models (LLMs) require enormous computing power to pretrain on massive datasets. When limited datasets are available, smaller-sized LLMs...
arXiv:2602.02634v1 Announce Type: new Abstract: We develop a reduction-based framework for online learning with delayed feedback that recovers and improves upon existing results for both...
arXiv:2602.02635v1 Announce Type: new Abstract: This paper proposes a graph-augmented reasoning framework for tobacco pest and disease management that integrates structured domain knowledge into large...
arXiv:2602.02636v1 Announce Type: new Abstract: Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under...
arXiv:2602.02638v1 Announce Type: new Abstract: High-resolution spatial transcriptomics platforms, such as Xenium, generate single-cell images that capture both molecular and spatial context, but their extremely...
arXiv:2602.02639v1 Announce Type: new Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning...
arXiv:2602.02640v1 Announce Type: new Abstract: The 2024 Bluebird Movement in Taiwan marked one of the largest youth-led protests in the country's democratic history, mobilizing over...
arXiv:2602.02641v1 Announce Type: new Abstract: The Uniform Resource Locator (URL), introduced in a connectivity-first era to define access and locate resources, remains historically limited, lacking...
arXiv:2602.02660v1 Announce Type: new Abstract: Automating AI research differs from general software engineering due to computationally expensive evaluation (e.g., model training) and opaque performance attribution....
arXiv:2602.02671v1 Announce Type: new Abstract: Machine learning force fields (MLFFs) have become essential for accurate and efficient atomistic modeling. Despite their high accuracy, most existing...
arXiv:2602.02676v1 Announce Type: new Abstract: Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual...
arXiv:2602.02680v1 Announce Type: new Abstract: The growing scale of deep neural networks, encompassing large language models (LLMs) and vision transformers (ViTs), has made training from...
arXiv:2602.02684v1 Announce Type: new Abstract: Audio description (AD) makes video content accessible to blind and low-vision (BLV) audiences, but producing high-quality descriptions is resource-intensive. Automated...