Knowledge tracing (KT) aims to trace students' knowledge states by predicting whether students answer correctly on exercises. Despite the excellent performance of existing Transformer-based KT approac ...
The Open Whisper-style Speech Models (OWSM) project has developed a series of fully open speech foundation models using academic-scale resources, but their training data remains insufficient. This wor ...
As inference workloads for large language models (LLMs) scale to meet growing user demand, pipeline parallelism (PP) has become a widely adopted strategy for multi-GPU deployment, particularly in cros ...
Machine learning (ML) tasks are one of the major workloads in today's edge computing networks. Existing edge-cloud schedulers allocate the requested amounts of resources to each task, falling short of ...
我们介绍了Reangle-A-Video,这是一个统一的框架,用于从单个输入视频中生成同步的多视频视频。与大规模4D数据集上训练多视频视频扩散模型的主流方法不同,我们的方法将多视频视频生成任务重新塑造为视频到视频翻译,利用公开可用的图像和视频扩散先验。从本质上讲,Reangle-A-Video分为两个阶段 ...
获取审阅者进行学术提交是一个具有挑战性的建议方案。最近以图形学习为驱动的模型在推荐领域取得了显着进步,但是他们在学术审稿人推荐任务中的表现可能会遭受重大的假负问题。这是由于未观察到的边缘代表负样本的假设 ...
为用户和项目学习有效的潜在表示是推荐系统的基石。传统方法依靠用户项目的交互数据将用户和项目映射到共享的潜在空间中,但是交互的稀疏通常会带来挑战。尽管利用用户评论可以减轻这种稀疏性,但现有的评论意见推荐模型通常显示出两个关键局限性 ...
各种现实世界的应用程序都依靠未来的信息来做出决策,因此要求有效,准确的长序列多元时间序列序列预测。尽管最近基于注意力的预测模型在捕获长期依赖方面表现出强大的能力,但它们仍然受到两个关键局限性。首先,规范的自我注意力具有二次复杂性w ...