Diffusion-based image editing models have demonstrated remarkable capabilities for generating high-quality results. However, the iterative inference process poses a significant challenge in achieving real-time generation. Previously proposed methods, such as feature caching or model distillation, often require model-specific designs and lack flexibility. In this paper, we introduce SA-Edit, an efficient, training-free, and plug-and-play algorithm for the universal acceleration of diffusion-based image editing models. Specifically, we propose a spatial scaling strategy to reduce redundant latent tokens and enhance efficiency. To address aliasing and blurring artifacts, we introduce a score-based filter and adaptively refine high-score regions after each upsampling operation. Our method achieves at least 4.2 × faster inference for image editing while maintaining high output quality. Furthermore, our approach can be seamlessly integrated with existing acceleration techniques to achieve even greater speedups. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method. The code is released at: https://github.com/ouroboros-phy/SA-Edit

Multivariate time series forecasting is critical for industrial applications such as predictive maintenance and anomaly detection. However, existing Transformer-based models often struggle to capture short-term residual patterns and are vulnerable to noise due to their uniform treatment of attention heads and lack of adaptability to input dynamics. To address these challenges, we propose the Residual Aggregation and Multi-Head Attention Reweighting Autoformer (RAMAR), an enhanced Autoformer-based architecture tailored for complex industrial environments. RAMAR introduces two complementary modules: the Local Residual Aggregator (LRA), which refines high-frequency residuals via bottleneck convolutions and gated fusion, and the Dynamic Head Reweighting Module (DHRM), which calibrates attention heads using multi-scale temporal–channel convolutions to suppress noisy activations and emphasize informative signals. Extensive experiments on three public ETT datasets demonstrate that RAMAR consistently outperforms strong baselines across multiple evaluation metrics, confirming its robustness and effectiveness for real-world industrial forecasting.

Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial anomaly synthesis (SIAS) has emerged as a promising alternative; however, existing methods struggle to balance sampling efficiency and generation quality. Moreover, most approaches treat all spatial regions uniformly, overlooking the distinct statistical differences between anomaly and background areas. This uniform treatment hinders the synthesis of controllable, structure-specific anomalies tailored for segmentation tasks. In this paper, we propose FAST, a foreground-aware diffusion framework featuring two novel modules: the Anomaly-Informed Accelerated Sampling (AIAS) and the Foreground-Aware Reconstruction Module (FARM). AIAS is a training-free sampling algorithm specifically designed for segmentation-oriented industrial anomaly synthesis, which accelerates the reverse process through coarse-to-fine aggregation and enables the synthesis of state-of-the-art segmentation-oriented anomalies in as few as 10 steps. Meanwhile, FARM adaptively adjusts the anomaly-aware noise within the masked foreground regions at each sampling step, preserving localized anomaly signals throughout the denoising trajectory. Extensive experiments on multiple industrial benchmarks demonstrate that FAST consistently outperforms existing anomaly synthesis methods in downstream segmentation tasks. We release the code in https://github.com/Chhro123/fast-foreground-aware-anomaly-synthesis.

End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications.During the training of end-to-end ASR, data augmentation is a quite effective technique for regularizing the neural networks.This paper proposes a novel data augmentation technique based on semantic transposition of the transcriptions via syntax rules for end-to-end Mandarin ASR.Specifically, we first segment the transcriptions based on part-of-speech tags.Then transposition strategies, such as placing the object in front of the subject or swapping the subject and the object, are applied on the segmented sentences.Finally, the acoustic features corresponding to the transposed transcription are reassembled based on the audio-to-text forced-alignment produced by a pre-trained ASR system.The combination of original data and augmented one is used for training a new ASR system.The experiments are conducted on the Transformer[1] and Conformer[2] based ASR.The results show that the proposed method can give consistent performance gain to the system.Augmentation related issues, such as comparison of different strategies and ratios for data combination are also investigated.