Stay updated with the latest research and technology news
arXiv:2509.26522v2 Announce Type: replace Abstract: Reasoning LLMs show improved performance with longer chains of thought. However, recent work has highlighted their tendency to overthink, continuing...
arXiv:2510.00167v2 Announce Type: replace Abstract: Autonomous drones must often respond to sudden events, such as alarms, faults, or unexpected changes in their environment, that require...
arXiv:2510.01931v4 Announce Type: replace Abstract: In a connected simple graph G = (V(G),E(G)), each vertex is assigned one of c colors, where V(G) can be...
arXiv:2510.02894v2 Announce Type: replace Abstract: PyRadiomics-cuda is a GPU-accelerated extension of the PyRadiomics library, designed to address the computational challenges of extracting three-dimensional shape features...
arXiv:2510.03352v2 Announce Type: replace Abstract: Diffusion models have been widely used as powerful priors for solving inverse problems. However, existing approaches typically overlook side information...
arXiv:2510.04080v2 Announce Type: replace Abstract: Conditional Semantic Textual Similarity (C-STS) measures the semantic proximity between text segments under a specific condition, thereby overcoming the ambiguity...
arXiv:2510.08886v2 Announce Type: replace Abstract: Going beyond simple text processing, financial auditing requires detecting semantic, structural, and numerical inconsistencies across large-scale disclosures. As financial reports...
arXiv:2510.09201v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown remarkable success, and their multimodal expansions (MLLMs) further unlock capabilities spanning images, videos, and...
arXiv:2510.12581v2 Announce Type: replace Abstract: We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies...
arXiv:2510.12915v2 Announce Type: replace Abstract: As the world becomes increasingly saturated with AI-generated content, disinformation, and algorithmic persuasion, critical thinking - the capacity to evaluate...
arXiv:2510.13582v2 Announce Type: replace Abstract: In advanced nodes, optimization of power, performance and area (PPA) has become highly complex and challenging. Machine learning (ML) and...
arXiv:2510.13749v2 Announce Type: replace Abstract: Chat assistants increasingly integrate web search functionality, enabling them to retrieve and cite external sources. While this promises more reliable...
arXiv:2510.14190v2 Announce Type: replace Abstract: Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control....
arXiv:2510.14974v3 Announce Type: replace Abstract: Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised...
arXiv:2510.15297v3 Announce Type: replace Abstract: We introduce VERA-MH (Validation of Ethical and Responsible AI in Mental Health), an automated evaluation of the safety of AI...
arXiv:2510.19771v3 Announce Type: replace Abstract: LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve...
arXiv:2510.20220v2 Announce Type: replace Abstract: Recent research has focused on mitigating algorithmic bias in clustering by incorporating fairness constraints into algorithmic design. Notions such as...
arXiv:2510.21081v2 Announce Type: replace Abstract: Deploying deep neural networks on mobile devices is increasingly important but remains challenging due to limited computing resources. On the...
arXiv:2510.21193v2 Announce Type: replace Abstract: The availability of LLM benchmarks for the Estonian language is limited, and a comprehensive evaluation comparing the performance of different...
arXiv:2510.24983v2 Announce Type: replace Abstract: Diffusion policies are competitive for offline reinforcement learning (RL) but are typically guided at sampling time by heuristics that lack...
arXiv:2510.25015v3 Announce Type: replace Abstract: We introduce VeriStruct, a novel framework that extends AI-assisted automated verification from single functions to more complex data structure modules...
arXiv:2510.25166v2 Announce Type: replace Abstract: Given the significant advances in machine learning techniques on mobile devices, particularly in the domain of computer vision, in this...
arXiv:2510.27118v2 Announce Type: replace Abstract: Most expressivity results for transformers treat them as language recognizers (which accept or reject strings), and not as they are...
arXiv:2511.00040v3 Announce Type: replace Abstract: The field of preference optimization has made outstanding contributions to the alignment of language models with human preferences. Despite these...