Zobrazeno 1 - 10
of 402
pro vyhledávání: '"Long, Mingsheng"'
We present Timer-XL, a generative Transformer for unified time series forecasting. To uniformly predict 1D and 2D time series, we generalize next token prediction, predominantly adopted for causal generation of 1D sequences, to multivariate next toke
Externí odkaz:
http://arxiv.org/abs/2410.04803
Time series forecasting is prevalent in extensive real-world applications, such as financial analysis and energy planning. Previous studies primarily focus on time series modality, endeavoring to capture the intricate variations and dependencies inhe
Externí odkaz:
http://arxiv.org/abs/2410.03806
Autor:
Feng, Ningya, Pan, Junwei, Wu, Jialong, Chen, Baixu, Wang, Ximei, Li, Qian, Hu, Xian, Jiang, Jie, Long, Mingsheng
Lifelong user behavior sequences, comprising up to tens of thousands of history behaviors, are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle th
Externí odkaz:
http://arxiv.org/abs/2410.02604
Time series, characterized by a sequence of data points arranged in a discrete-time order, are ubiquitous in real-world applications. Different from other modalities, time series present unique challenges due to their complex and dynamic nature, incl
Externí odkaz:
http://arxiv.org/abs/2407.13278
Diffusion models have significantly advanced the field of generative modeling. However, training a diffusion model is computationally expensive, creating a pressing need to adapt off-the-shelf diffusion models for downstream generation tasks. Current
Externí odkaz:
http://arxiv.org/abs/2406.00773
Deep models have recently emerged as a promising tool to solve partial differential equations (PDEs), known as neural PDE solvers. While neural solvers trained from either simulation data or physics-informed loss can solve PDEs reasonably well, they
Externí odkaz:
http://arxiv.org/abs/2405.17527
World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in video gen
Externí odkaz:
http://arxiv.org/abs/2405.15223
Physics-informed neural networks (PINNs) have been widely applied to solve partial differential equations (PDEs) by enforcing outputs and gradients of deep models to satisfy target equations. Due to the limitation of numerical computation, PINNs are
Externí odkaz:
http://arxiv.org/abs/2405.14369
Predictive Coding (PC) is a theoretical framework in cognitive science suggesting that the human brain processes cognition through spatiotemporal prediction of the visual world. Existing studies have developed spatiotemporal prediction neural network
Externí odkaz:
http://arxiv.org/abs/2405.02384
Effective code optimization in compilers is crucial for computer and software engineering. The success of these optimizations primarily depends on the selection and ordering of the optimization passes applied to the code. While most compilers rely on
Externí odkaz:
http://arxiv.org/abs/2404.16077