Stay updated with the latest research and technology news
arXiv:2508.04609v2 Announce Type: replace Abstract: Accelerating the solution of linear systems of equations is critical due to their central role in numerous applications, such as...
arXiv:2508.04945v2 Announce Type: replace Abstract: Evaluating visual activity recognition systems is challenging due to inherent ambiguities in verb semantics and image interpretation. When describing actions...
arXiv:2508.06030v2 Announce Type: replace Abstract: Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However,...
arXiv:2508.06515v3 Announce Type: replace Abstract: Social media platforms face escalating challenges in detecting harmful content that promotes muscle dysmorphic behaviors and cognitions (bigorexia). This content...
arXiv:2508.06753v2 Announce Type: replace Abstract: The advent of ultra-low-bit LLM models (1/1.58/2-bit), which match the perplexity and end-task performance of their full-precision counterparts using the...
arXiv:2508.07229v3 Announce Type: replace Abstract: Despite their success in speech processing, neural networks often operate as black boxes, prompting the question: what informs their decisions,...
arXiv:2508.08487v5 Announce Type: replace Abstract: Despite recent advances, long-sequence video generation frameworks still suffer from significant limitations: poor assistive capability, suboptimal visual quality, and limited...
arXiv:2508.10157v2 Announce Type: replace Abstract: Pre-trained language models (PTLMs) have transformed natural language processing (NLP), enabling major advances in tasks such as text generation and...
arXiv:2508.11565v2 Announce Type: replace Abstract: Feature interaction is a core ingredient in ranking models for large-scale recommender systems, yet making it both expressive and efficiently...
arXiv:2508.11669v2 Announce Type: replace Abstract: Noninvasive arterial blood pressure (ABP) monitoring is essential for patient management in critical care and perioperative settings, providing continuous assessment...
arXiv:2508.11808v2 Announce Type: replace Abstract: Online hate remains a significant societal challenge, especially as multimodal content enables subtle, culturally grounded, and implicit forms of harm....
arXiv:2508.12730v3 Announce Type: replace Abstract: Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer...
arXiv:2508.13968v3 Announce Type: replace Abstract: We investigate to what extent Multimodal Large Language Models (MLLMs) can accurately identify the orientation of input images rotated 0{\deg},...
arXiv:2508.15304v2 Announce Type: replace Abstract: Multimodal recommendation combines the user historical behaviors with the modal features of items to capture the tangible user preferences, presenting...
arXiv:2508.15338v2 Announce Type: replace Abstract: Electrocardiography (ECG) plays a central role in cardiovascular diagnostics, yet existing automated approaches often struggle to generalize across clinical tasks...
arXiv:2508.15356v2 Announce Type: replace Abstract: A strategy profile in a multi-player game is a Nash equilibrium if no player can unilaterally deviate to achieve a...
arXiv:2508.15830v2 Announce Type: replace Abstract: Recent evaluations of Large language models (LLMs) audit social bias primarily through prompts that explicitly reference demographic attributes, overlooking whether...
arXiv:2508.16738v2 Announce Type: replace Abstract: Zero-Knowledge Proofs (ZKPs) have emerged as a powerful tool for secure and privacy-preserving computation. ZKPs enable one party to convince...
arXiv:2508.16984v2 Announce Type: replace Abstract: Diffusion models have achieved remarkable success in content generation but often incur prohibitive computational costs due to iterative sampling. Recent...
arXiv:2508.17218v2 Announce Type: replace Abstract: With the rapidly increased number of vehicles in urban areas, existing road infrastructure struggles to accommodate modern traffic demands, resulting...
arXiv:2508.18741v2 Announce Type: replace Abstract: Offline reinforcement learning and offline inverse reinforcement learning aim to recover near-optimal value functions or reward models from a fixed...
arXiv:2508.18880v2 Announce Type: replace Abstract: Large Language Models (LLMs) are being integrated into professional domains, yet their limitations in such high-stakes fields as law remain...
arXiv:2508.18989v2 Announce Type: replace Abstract: As Vision Language Models (VLMs) become integral to real-world applications, understanding their demographic biases is critical. We introduce GRAS, a...
arXiv:2508.19008v2 Announce Type: replace Abstract: Building on a human-led thematic analysis of life-story interviews with inpatients with Borderline Personality Disorder, this study examines the capacity...