English
Related papers

Related papers: Shared DIFF Transformer

200 papers

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…

Image and Video Processing · Electrical Eng. & Systems 2023-03-21 Xiangyu Chen , Xintao Wang , Jiantao Zhou , Yu Qiao , Chao Dong

We propose DiffQ a differentiable method for model compression for quantizing model parameters without gradient approximations (e.g., Straight Through Estimator). We suggest adding independent pseudo quantization noise to model parameters…

Machine Learning · Statistics 2022-10-18 Alexandre Défossez , Yossi Adi , Gabriel Synnaeve

In this paper, we introduce \texttt{IAFormer}, a novel Transformer-based architecture that efficiently integrates pairwise particle interactions through a dynamic sparse attention mechanism. \texttt{IAFormer} has two new mechanisms within…

High Energy Physics - Phenomenology · Physics 2026-04-21 W. Esmail , A. Hammad , M. Nojiri

This paper proposes DiffPF, a differentiable particle filter that leverages diffusion models for state estimation in dynamic systems. Unlike conventional differentiable particle filters, which require importance weighting and typically rely…

Robotics · Computer Science 2026-01-13 Ziyu Wan , Lin Zhao

This paper introduces Generalized Attention Flow (GAF), a novel feature attribution method for Transformer-based models to address the limitations of current approaches. By extending Attention Flow and replacing attention weights with the…

Machine Learning · Computer Science 2025-02-25 Behrooz Azarkhalili , Maxwell Libbrecht

Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong…

Machine Learning · Computer Science 2025-03-04 Xingzhuo Guo , Yu Zhang , Baixu Chen , Haoran Xu , Jianmin Wang , Mingsheng Long

Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct…

Computation and Language · Computer Science 2026-03-10 J. Clayton Kerce , Alexis Fox

This paper presents StrADiff, a Structured Source-Wise Adaptive Diffusion Framework for unsupervised blind source separation under linear and nonlinear mixing. The framework treats each latent dimension as a source branch and assigns to it…

Machine Learning · Statistics 2026-04-29 Yuan-Hao Wei

We propose Beat Transformer, a novel Transformer encoder architecture for joint beat and downbeat tracking. Different from previous models that track beats solely based on the spectrogram of an audio mixture, our model deals with demixed…

Sound · Computer Science 2022-09-16 Jingwei Zhao , Gus Xia , Ye Wang

Side information fusion for sequential recommendation (SR) aims to effectively leverage various side information to enhance the performance of next-item prediction. Most state-of-the-art methods build on self-attention networks and focus on…

Information Retrieval · Computer Science 2022-04-26 Yueqi Xie , Peilin Zhou , Sunghun Kim

In this work, we propose a novel framework to enable diffusion models to adapt their generation quality based on real-time network bandwidth constraints. Traditional diffusion models produce high-fidelity images by performing a fixed number…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Xi Zhang , Hanwei Zhu , Yan Zhong , Jiamang Wang , Weisi Lin

Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction under multi-speaker noisy conditions remains relatively…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-08 Leying Zhang , Yao Qian , Linfeng Yu , Heming Wang , Hemin Yang , Long Zhou , Shujie Liu , Yanmin Qian

Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Gwanghyun Kim , Alonso Martinez , Yu-Chuan Su , Brendan Jou , José Lezama , Agrim Gupta , Lijun Yu , Lu Jiang , Aren Jansen , Jacob Walker , Krishna Somandepalli

We present a method that reduces, by an order of magnitude, the time and memory needed to train multi-task vision-language robotic diffusion policies. This improvement arises from a previously underexplored distinction between action…

Robotics · Computer Science 2025-06-06 Yutong Hu , Pinhao Song , Kehan Wen , Renaud Detry

Neural beamformers, which integrate both pre-separation and beamforming modules, have demonstrated impressive effectiveness in target speech extraction. Nevertheless, the performance of these beamformers is inherently limited by the…

Sound · Computer Science 2023-09-08 Aoqi Guo , Sichong Qian , Baoxiang Li , Dazhi Gao

The capability to transfer mastered skills to accomplish a range of similar yet novel tasks is crucial for intelligent robots. In this work, we introduce $\textit{Diff-Transfer}$, a novel framework leveraging differentiable physics…

Robotics · Computer Science 2023-10-11 Yuqi Xiang , Feitong Chen , Qinsi Wang , Yang Gang , Xiang Zhang , Xinghao Zhu , Xingyu Liu , Lin Shao

Small language models have gained significant popularity due to their efficiency and growing capabilities. However, incorporating additional modalities, such as vision, can exacerbate the challenge of limited context windows by introducing…

Artificial Intelligence · Computer Science 2025-07-23 Jerry Li , Timothy Oh , Joseph Hoang , Vardhit Veeramachaneni

We introduce DP-FinDiff, a differentially private diffusion framework for synthesizing mixed-type tabular data. DP-FinDiff employs embedding-based representations for categorical features, reducing encoding overhead and scaling to…

Machine Learning · Computer Science 2025-12-02 Timur Sattarov , Marco Schreyer , Damian Borth

The goal of speech enhancement (SE) is to eliminate the background interference from the noisy speech signal. Generative models such as diffusion models (DM) have been applied to the task of SE because of better generalization in unseen…

Sound · Computer Science 2023-09-06 Wen Wang , Dongchao Yang , Qichen Ye , Bowen Cao , Yuexian Zou

Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Zhihao Shi , Xiangyu Xu , Xiaohong Liu , Jun Chen , Ming-Hsuan Yang
‹ Prev 1 4 5 6 7 8 10 Next ›