Despite a growing interest in diffusion-based language models, existing work has not shown that these models can attain nontrivial likelihoods on standard language modeling …
Current AI-assisted protein design mainly utilizes protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in the text …
Spatio-temporal point process (STPP) is a stochastic collection of events accompanied with time and space. Due to computational complexities, existing solutions for STPPs …
J Ye, Z Zheng, Y Bao, L Qian, M Wang - arXiv preprint arXiv:2302.10025, 2023 - arxiv.org
While diffusion models have achieved great success in generating continuous signals such as images and audio, it remains elusive for diffusion models in learning discrete sequence …
Non-autoregressive (NAR) text generation has attracted much attention in the field of natural language processing, which greatly reduces the inference latency but has to sacrifice the …
Diffusion models that are based on iterative denoising have been recently proposed and leveraged in various generation tasks like image generation. Whereas, as a way inherently …
T Wei, Y Lin, S Guo, Y Lin, Y Huang… - … on Knowledge and …, 2024 - ieeexplore.ieee.org
Trajectory data is essential for various applications. However, publicly available trajectory datasets remain limited in scale due to privacy concerns, which hinders the development of …
Y Wang, Z Liu, L Yang, PS Yu - … on Knowledge Discovery and Data Mining, 2024 - Springer
Contemporary attention-based sequential recommendations often encounter the oversmoothing problem, which generates indistinguishable representations. Although …
The sharing of microdata, such as fund holdings and derivative instruments, by regulatory institutions presents a unique challenge due to strict data confidentiality and privacy …