Accelerating diffusion sampling with optimized time steps

S Xue, Z Liu, F Chen, S Zhang, T Hu… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Diffusion probabilistic models (DPMs) have shown remarkable performance in high-
resolution image synthesis but their sampling efficiency is still to be desired due to the …

Sa-solver: Stochastic adams solver for fast sampling of diffusion models

S Xue, M Yi, W Luo, S Zhang, J Sun… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
Abstract Diffusion Probabilistic Models (DPMs) have achieved considerable success in
generation tasks. As sampling from DPMs is equivalent to solving diffusion SDE or ODE …

CTFNet: Long-sequence time-series forecasting based on convolution and time–frequency analysis

Z Zhang, Y Chen, D Zhang, Y Qian… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Although current time-series forecasting methods have significantly improved the state-of-
the-art (SOTA) results for long-sequence time-series forecasting (LSTF), they still have …

The double-edged sword of exemplar similarity

M Majzoubi, EY Zhao, T Zuzul… - Organization …, 2025‏ - pubsonline.informs.org
We investigate how a firm's positioning relative to category exemplars shapes security
analysts' evaluations. Using a two-stage model of evaluation (initial screening and …

Multi-level knowledge distillation for out-of-distribution detection in text

Q Wu, H Jiang, H Yin, BF Karlsson, CY Lin - arxiv preprint arxiv …, 2022‏ - arxiv.org
Self-supervised representation learning has proved to be a valuable component for out-of-
distribution (OoD) detection with only the texts of in-distribution (ID) examples. These …

HTAP databases: A survey

C Zhang, G Li, J Zhang, X Zhang… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Since Gartner coined the term, Hybrid Transactional and Analytical Processing (HTAP),
numerous HTAP databases have been proposed to combine transactions with analytics in …

Hypr: A comprehensive study for asr hypothesis revising with a reference corpus

YW Wang, KH Lu, KY Chen - arxiv preprint arxiv:2309.09838, 2023‏ - arxiv.org
With the development of deep learning, automatic speech recognition (ASR) has made
significant progress. To further enhance the performance of ASR, revising recognition results …

End-to-end word-level pronunciation assessment with MASK pre-training

Y Liang, K Song, S Mao, H Jiang, L Qiu, Y Yang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Pronunciation assessment is a major challenge in the computer-aided pronunciation
training system, especially at the word (phoneme)-level. To obtain word (phoneme)-level …

PFDiff: Training-free Acceleration of Diffusion Models through the Gradient Guidance of Past and Future

G Wang, Y Cai, L Li, W Peng, S Su - arxiv preprint arxiv:2408.08822, 2024‏ - arxiv.org
Diffusion Probabilistic Models (DPMs) have shown remarkable potential in image
generation, but their sampling efficiency is hindered by the need for numerous denoising …

Diffusion Sampling Correction via Approximately 10 Parameters

G Wang, W Peng, L Li, W Chen, Y Cai, S Su - arxiv preprint arxiv …, 2024‏ - arxiv.org
Diffusion Probabilistic Models (DPMs) have demonstrated exceptional performance in
generative tasks, but this comes at the expense of sampling efficiency. To enhance sampling …