Stay updated with the latest research and technology news
arXiv:2410.19806v3 Announce Type: replace Abstract: Recent advancements in generative AI, such as ChatGPT, have dramatically transformed how people access information. Despite its powerful capabilities, the...
arXiv:2410.22242v3 Announce Type: replace Abstract: The Betti tables of a multigraded module encode the grades at which there is an algebraic change in the module....
arXiv:2411.06403v3 Announce Type: replace Abstract: We study impartial games under fixed-latency, fixed-scale quantised inference (FSQI). In this fixed-scale, bounded-range regime, we prove that inference is...
arXiv:2411.07194v5 Announce Type: replace Abstract: We propose a novel algorithm for calculating the ground-state energy of quantum many-body systems by combining auxiliary-field quantum Monte Carlo...
arXiv:2411.08982v2 Announce Type: replace Abstract: Selective parameter activation provided by Mixture-of-Expert (MoE) models have made them a popular choice in modern foundational models. However, MoEs...
arXiv:2411.16085v4 Announce Type: replace Abstract: AdamW has been the default optimizer for transformer pretraining. For many years, our community searched for faster and more stable...
arXiv:2412.00686v4 Announce Type: replace Abstract: Counting is a fundamental operation for various real-world visual tasks, requiring both object recognition and robust counting capabilities. Despite their...
arXiv:2412.06082v3 Announce Type: replace Abstract: Recent advances in self-supervision and contrastive learning have brought the performance of foundation models to unprecedented levels in a variety...
arXiv:2412.09950v2 Announce Type: replace Abstract: Users' interactions with recommender systems often involve more than simple acceptance or rejection. We highlight two overlooked states: hesitation, when...
arXiv:2412.11439v5 Announce Type: replace Abstract: Generating novel molecules with higher properties than the training space, namely the out-of-distribution generation, is important for de novo drug...
arXiv:2412.11586v4 Announce Type: replace Abstract: While haircut indicates distinct personality, existing avatar generation methods fail to model practical hair due to the data limitation or...
arXiv:2412.14294v2 Announce Type: replace Abstract: We propose a novel block for \emph{causal} video modelling. It relies on a time-space-channel factorisation with dedicated blocks for each...
arXiv:2412.19401v3 Announce Type: replace Abstract: Shared autonomous vehicles (SAVs) bring competition to traditional transit services but redesigning multimodal transit network can utilize SAVs as feeders...
arXiv:2412.20110v4 Announce Type: replace Abstract: Few-shot image classification remains a critical challenge in the field of computer vision, particularly in data-scarce environments. Existing methods typically...
arXiv:2501.05633v2 Announce Type: replace Abstract: Error accumulation is effective for gradient sparsification in distributed settings: initially-unselected gradient entries are eventually selected as their accumulated error...
arXiv:2501.07575v2 Announce Type: replace Abstract: Dataset distillation aims to synthesize a compact yet representative dataset that preserves the essential characteristics of the original data for...
arXiv:2501.12816v2 Announce Type: replace Abstract: This work presents an overview of several nonlinear reduction strategies for data compression from various research fields, and a comparison...
arXiv:2501.15889v5 Announce Type: replace Abstract: For almost 70 years, researchers have typically selected the width of neural networks' layers either manually or through automated hyperparameter...
arXiv:2501.16178v3 Announce Type: replace Abstract: In recent work on time-series prediction, Transformers and even large language models have garnered significant attention due to their strong...
arXiv:2501.16909v3 Announce Type: replace Abstract: GPUs are vastly underutilized, even when running resource-intensive AI applications, as GPU kernels within each job have diverse resource profiles...
arXiv:2502.01594v2 Announce Type: replace Abstract: Adaptive optimization algorithms -- such as Adagrad, Adam, and their variants -- have found widespread use in machine learning, signal...
arXiv:2502.01713v4 Announce Type: replace Abstract: Algorithms are increasingly used to automate or aid human decisions, yet recent research shows that these algorithms may exhibit bias...
arXiv:2502.02415v2 Announce Type: replace Abstract: Existing graph generative models often face a critical trade-off between sample quality and generation speed. We introduce Autoregressive Noisy Filtration...
arXiv:2502.04947v5 Announce Type: replace Abstract: In this work, we present a study combining two approaches in the context of solving PDEs: the continuous finite element...