English
Related papers

Related papers: Shared DIFF Transformer

200 papers

Although transformer has achieved great progress on computer vision tasks, the scale variation in dense image prediction is still the key challenge. Few effective multi-scale techniques are applied in transformer and there are two main…

Computer Vision and Pattern Recognition · Computer Science 2021-09-21 Zekun Li , Yufan Liu , Bing Li , Weiming Hu , Kebin Wu , Pei Wang

Transformers have demonstrated exceptional performance across various domains due to their self-attention mechanism, which captures complex relationships in data. However, training on smaller datasets poses challenges, as standard attention…

Computation and Language · Computer Science 2024-12-10 Minhajur Rahman , Yasir Arafat

Time series forecasting has various applications, such as meteorological rainfall prediction, traffic flow analysis, financial forecasting, and operational load monitoring for various systems. Due to the sparsity of time series data,…

Machine Learning · Computer Science 2025-10-01 Xiaojian Wang , Chaoli Zhang , Zhonglong Zheng , Yunliang Jiang

Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-24 Runwu Shi , Chang Li , Jiang Wang , Rui Zhang , Nabeela Khan , Benjamin Yen , Takeshi Ashizawa , Kazuhiro Nakadai

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

Diffusion models have garnered significant interest from the community for their great generative ability across various applications. However, their typical multi-step sequential-denoising nature gives rise to high cumulative latency,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Zigeng Chen , Xinyin Ma , Gongfan Fang , Zhenxiong Tan , Xinchao Wang

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

Computation and Language · Computer Science 2025-06-16 Hanzhi Zhang , Heng Fan , Kewei Sha , Yan Huang , Yunhe Feng

Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space. In this paper, we conduct systematic studies of the…

Computation and Language · Computer Science 2024-04-23 Zhujin Gao , Junliang Guo , Xu Tan , Yongxin Zhu , Fang Zhang , Jiang Bian , Linli Xu

We propose Diffusion Inference-Time T-Optimization (DITTO), a general-purpose frame-work for controlling pre-trained text-to-music diffusion models at inference-time via optimizing initial noise latents. Our method can be used to optimize…

Sound · Computer Science 2024-06-04 Zachary Novack , Julian McAuley , Taylor Berg-Kirkpatrick , Nicholas J. Bryan

In partially observable multi-agent systems, agents typically only have access to local observations. This severely hinders their ability to make precise decisions, particularly during decentralized execution. To alleviate this problem and…

Multiagent Systems · Computer Science 2024-08-20 Zhiwei Xu , Hangyu Mao , Nianmin Zhang , Xin Xin , Pengjie Ren , Dapeng Li , Bin Zhang , Guoliang Fan , Zhumin Chen , Changwei Wang , Jiangjin Yin

Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding and require a lot of learnable parameters. This paper explores Transformer-based speech separation…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-17 Luca Della Libera , Cem Subakan , Mirco Ravanelli , Samuele Cornell , Frédéric Lepoutre , François Grondin

Deep Neural Network-based source separation methods usually train independent models to optimize for the separation of individual sources. Although this can lead to good performance for well-defined targets, it can also be computationally…

Sound · Computer Science 2019-08-15 Clement S. J. Doire , Olumide Okubadejo

Fine-tuning plays a crucial role in adapting models to downstream tasks with minimal training efforts. However, the rapidly increasing size of foundation models poses a daunting challenge for accommodating foundation model fine-tuning in…

Machine Learning · Computer Science 2025-04-18 Shiwei Ding , Lan Zhang , Zhenlin Wang , Giuseppe Ateniese , Xiaoyong Yuan

Transformer-based neural decoders have emerged as a promising approach to error correction coding, combining data-driven adaptability with efficient modeling of long-range dependencies. This paper presents a novel decoder architecture that…

Information Theory · Computer Science 2025-09-22 Chin Wa Lau , Xiang Shi , Ziyan Zheng , Haiwen Cao , Nian Guo

Recent work on encoder-decoder models for sequence-to-sequence mapping has shown that integrating both temporal and spatial attention mechanisms into neural networks increases the performance of the system substantially. In this work, we…

Machine Learning · Computer Science 2017-08-04 Stefan Braun , Daniel Neil , Enea Ceolini , Jithendar Anumula , Shih-Chii Liu

Conditional diffusion models have made impressive progress in the field of image processing, but the characteristics of constructing data distribution pathways make it difficult to exploit the intrinsic correlation between tasks in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Chengjie Huang , Jiafeng Yan , Jing Li , Lu Bai

Transformer-based Super-Resolution (SR) methods have demonstrated superior performance compared to convolutional neural network (CNN)-based SR approaches due to their capability to capture long-range dependencies. However, their high…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Karam Park , Jae Woong Soh , Nam Ik Cho

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

Image restoration has witnessed significant advancements with the development of deep learning models. Transformer-based models, particularly those using window-based self-attention, have become a dominant force. However, their performance…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Gang Wu , Junjun Jiang , Kui Jiang , Xianming Liu , Liqiang Nie

Data imputation and data generation have important applications for many domains, like healthcare and finance, where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emerged as powerful…

Machine Learning · Computer Science 2025-06-10 Mario Villaizán-Vallelado , Matteo Salvatori , Carlos Segura , Ioannis Arapakis