Stay updated with the latest research and technology news
arXiv:2504.16315v3 Announce Type: replace Abstract: The complexity of sign language data processing brings many challenges. The current approach to recognition of ASL signs aims to...
arXiv:2504.18677v2 Announce Type: replace Abstract: Randomized quasi-Monte Carlo (RQMC) methods estimate the mean of a random variable by sampling an integrand at $n$ equidistributed points....
arXiv:2504.18881v3 Announce Type: replace Abstract: A primary challenge in ITE estimation is sample selection bias. Traditional approaches utilize treatment regularization techniques such as the Integral...
arXiv:2504.19110v3 Announce Type: replace Abstract: While frontier formal mathematics systems now routinely develop repository-scale proof engineering artifacts requiring multi-file coordination and semantic correctness beyond compilation,...
arXiv:2504.19472v2 Announce Type: replace Abstract: As NLP models become increasingly integrated into real-world applications, it becomes clear that there is a need to address the...
arXiv:2505.00823v2 Announce Type: replace Abstract: Phase change process plays a critical role in thermal management systems, yet quantitative characterization of multiphase heat transfer remains limited...
arXiv:2505.01807v3 Announce Type: replace Abstract: We aim to approximate a continuously differentiable function $u:\mathbb{R}^d \rightarrow \mathbb{R}$ by a composition of functions $f\circ g$ where $g:\mathbb{R}^d...
arXiv:2505.01892v5 Announce Type: replace Abstract: The ONNX Optimizer, part of the official ONNX repository and widely adopted for graph-level model optimizations, is used by default...
arXiv:2505.05064v2 Announce Type: replace Abstract: Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of...
arXiv:2505.05203v2 Announce Type: replace Abstract: With the increasing penetration of renewable energy, traditional physics-based power system operation faces growing challenges in achieving economic efficiency, stability,...
arXiv:2505.06091v2 Announce Type: replace Abstract: Symbolic Regression (SR) is a powerful technique for automatically discovering mathematical expressions from input data. Mainstream SR algorithms search for...
arXiv:2505.06795v4 Announce Type: replace Abstract: Commodity futures are volatile. Forecasting across horizons with interpretable drivers remains challenging. We propose the Sparse Latent Factor Forecaster with...
arXiv:2505.08088v3 Announce Type: replace Abstract: Vertical localization, particularly floor separation, remains a major challenge in indoor positioning systems operating in GPS-denied multistory environments. This paper...
arXiv:2505.08258v2 Announce Type: replace Abstract: Indoor position technology has become one of the research highlights in the Internet of Things (IoT), but there is still...
arXiv:2505.09134v2 Announce Type: replace Abstract: We present a scalable Gaussian Process (GP) method called DSoftKI that can fit and predict full derivative observations. It extends...
arXiv:2505.10007v3 Announce Type: replace Abstract: Motivated by practical applications where stable long-term performance is critical-such as robotics, operations research, and healthcare-we study the problem of...
arXiv:2505.10860v2 Announce Type: replace Abstract: Mixture of experts (MoE) methods are a key component in most large language model architectures, including the recent series of...
arXiv:2505.11614v2 Announce Type: replace Abstract: A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight...
arXiv:2505.11884v2 Announce Type: replace Abstract: Face recognition performance based on deep learning heavily relies on large-scale training data, which is often difficult to acquire in...
arXiv:2505.11891v3 Announce Type: replace Abstract: VLM-based mobile agents are increasingly popular due to their capabilities to interact with smartphone GUIs and XML-structured texts and to...
arXiv:2505.12742v3 Announce Type: replace Abstract: Essential to visual generation is efficient modeling of visual data priors. Conventional next-token prediction methods define the process as learning...
arXiv:2505.13192v3 Announce Type: replace Abstract: Complex, temporally evolving phenomena, from climate to brain activity, are governed by dynamical systems (DS). DS reconstruction (DSR) seeks to...
arXiv:2505.13255v5 Announce Type: replace Abstract: Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their...
arXiv:2505.13811v2 Announce Type: replace Abstract: Fine-tuning a language model often results in a degradation of its existing performance on other tasks, due to a shift...