Stay updated with the latest research and technology news
arXiv:2503.04582v3 Announce Type: replace Abstract: Distribution shift poses a significant challenge in machine learning, particularly in biomedical applications using data collected across different subjects, institutions,...
arXiv:2503.07392v4 Announce Type: replace Abstract: Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement,...
arXiv:2503.09158v4 Announce Type: replace Abstract: Existing video large language models (VLLMs) primarily leverage prompt agnostic visual encoders, which extract untargeted facial representations without awareness of...
arXiv:2503.09630v4 Announce Type: replace Abstract: Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually...
arXiv:2503.11947v4 Announce Type: replace Abstract: The rapid expansion of Artificial Intelligence (AI) in digital platforms used by youth has created significant challenges related to privacy,...
arXiv:2503.17229v3 Announce Type: replace Abstract: Large Language Models (LLMs) frequently generate hallucinated content, posing significant challenges for applications where factuality is crucial. While existing hallucination...
arXiv:2503.20654v2 Announce Type: replace Abstract: Collecting real-world vehicle accident videos for autonomous driving research is challenging due to their rarity and complexity. While existing driving...
arXiv:2504.00757v2 Announce Type: replace Abstract: Nuclear reactor buildings must be designed to withstand the dynamic load induced by strong ground motion earthquakes. For this reason,...
arXiv:2504.01443v2 Announce Type: replace Abstract: Unmanned aerial vehicles (UAVs) with integrated sensing, communication, computation and control (ISC3) capabilities have become key enablers of next-generation wireless...
arXiv:2504.01987v3 Announce Type: replace Abstract: In autonomous systems, sensor calibration is essential for safe and efficient navigation in dynamic environments. Accurate calibration is a prerequisite...
arXiv:2504.06235v4 Announce Type: replace Abstract: Much of federated learning (FL) focuses on settings where local dataset statistics remain the same between training and testing. However,...
arXiv:2504.07733v2 Announce Type: replace Abstract: Motivated by the emerging adoption of Large Language Models (LLMs) in economics and management research, this paper investigates whether LLMs...
arXiv:2504.08365v3 Announce Type: replace Abstract: Sound Event Localization and Detection (SELD) combines the Sound Event Detection (SED) with the corresponding Direction Of Arrival (DOA). Recently,...
arXiv:2504.09026v3 Announce Type: replace Abstract: Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets,...
arXiv:2504.09378v3 Announce Type: replace Abstract: Large language models (LLMs) can answer prompts in many languages, despite being trained predominantly on English; yet, the mechanisms driving...
arXiv:2504.14366v3 Announce Type: replace Abstract: Linearization has emerged as a strategy for developing efficient language models (LMs). Starting from an existing Transformer-based LM, linearization replaces...
arXiv:2504.14623v2 Announce Type: replace Abstract: Asynchronous automata are a model of distributed finite state processes synchronising on shared actions. A celebrated result by Zielonka shows...
arXiv:2504.19116v2 Announce Type: replace Abstract: This paper analyses the classical mixed finite element method (FEM) and a pressure-robust variant with divergence-free reconstruction operators for the...
arXiv:2504.19602v4 Announce Type: replace Abstract: Federated Learning (FL) enables collaborative model training across decentralized clients, enhancing privacy by keeping data local. Yet conventional FL, relying...
arXiv:2505.04769v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models mark a transformative advancement in artificial intelligence, aiming to unify perception, natural language understanding, and embodied action...
arXiv:2505.07527v4 Announce Type: replace Abstract: The advantage function is a central concept in RL that helps reduce variance in policy gradient estimates. Recently, for language...
arXiv:2505.08140v5 Announce Type: replace Abstract: Despite their many successes, transformer-based large language models (LLMs) continue to struggle with tasks that require complex reasoning over large...
arXiv:2505.11480v3 Announce Type: replace Abstract: Superoptimization is the task of transforming a program into a faster one while preserving its input-output behavior. In this work,...
arXiv:2505.11809v2 Announce Type: replace Abstract: Visibility analysis is one of the fundamental analytics methods in urban planning and landscape research, traditionally conducted through computational simulations...