中文
相关论文

相关论文: Unleashing the Potential of Two-Tower Models: Diff…

200 篇论文

This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation,…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Yifan Pu , Zhuofan Xia , Jiayi Guo , Dongchen Han , Qixiu Li , Duo Li , Yuhui Yuan , Ji Li , Yizeng Han , Shiji Song , Gao Huang , Xiu Li

Distributed diffusion is a powerful algorithm for multi-task state estimation which enables networked agents to interact with neighbors to process input data and diffuse information across the network. Compared to a centralized approach,…

多智能体系统 · 计算机科学 2020-03-27 Jiani Li , Xenofon Koutsoukos

Talking head generation with arbitrary identities and speech audio remains a crucial problem in the realm of the virtual metaverse. Recently, diffusion models have become a popular generative technique in this field with their strong…

图形学 · 计算机科学 2025-08-11 Xinyang Li , Gen Li , Zhihui Lin , Yichen Qian , GongXin Yao , Weinan Jia , Aowen Wang , Weihua Chen , Fan Wang

Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either…

计算机视觉与模式识别 · 计算机科学 2023-03-17 Xixi Wang , Xiao Wang , Bo Jiang , Jin Tang , Bin Luo

Recent advancements in text-to-image diffusion models have significantly transformed visual content generation, yet their application in specialized fields such as interior design remains underexplored. In this paper, we present…

计算机视觉与模式识别 · 计算机科学 2024-09-06 Zhaowei Wang , Ying Hao , Hao Wei , Qing Xiao , Lulu Chen , Yulong Li , Yue Yang , Tianyi Li

Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory.…

计算机视觉与模式识别 · 计算机科学 2024-06-11 Yi Gu , Zhendong Wang , Yueqin Yin , Yujia Xie , Mingyuan Zhou

Data Augmentation (DA), i.e., synthesizing faithful and diverse samples to expand the original training set, is a prevalent and effective strategy to improve the performance of various data-scarce tasks. With the powerful image generation…

计算机视觉与模式识别 · 计算机科学 2024-11-22 Yanghao Wang , Long Chen

Recent developments in deep generative models have opened up a wide range of opportunities for image synthesis, leading to significant changes in various creative fields, including the fashion industry. While numerous methods have been…

计算机视觉与模式识别 · 计算机科学 2024-07-08 Ajda Lampe , Julija Stopar , Deepak Kumar Jain , Shinichiro Omachi , Peter Peer , Vitomir Štruc

Online video services acquire new content on a daily basis to increase engagement, and improve the user experience. Traditional recommender systems solely rely on watch history, delaying the recommendation of newly added titles to the right…

信息检索 · 计算机科学 2022-04-05 Jianling Wang , Ainur Yessenalina , Alireza Roshan-Ghias

Recent years have witnessed extensive researches on developing two tower recommendation models for relieving information overload. Four building modules can be identified in such models, namely, user-item encoding, negative sampling, loss…

信息检索 · 计算机科学 2024-10-10 Erjia Chen , Bang Wang

This paper proposes MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy, a control policy for active multi-target tracking using a mobile agent. The policy enables multiple behavior modes for the agent, including exploration,…

机器人学 · 计算机科学 2026-04-23 Saida Liu , Nikolay Atanasov , Shumon Koga

The goal of diffusion generative models is to align the learned distribution with the real data distribution through gradient score matching. However, inherent limitations in training data quality, modeling strategies, and architectural…

机器学习 · 计算机科学 2025-04-25 Lichen Bai , Masashi Sugiyama , Zeke Xie

The objective for establishing dense correspondence between paired images consists of two terms: a data term and a prior term. While conventional techniques focused on defining hand-designed prior terms, which are difficult to formulate,…

计算机视觉与模式识别 · 计算机科学 2024-01-26 Jisu Nam , Gyuseong Lee , Sunwoo Kim , Hyeonsu Kim , Hyoungwon Cho , Seyeon Kim , Seungryong Kim

Diffusion Transformers (DiTs) with billions of model parameters form the backbone of popular image and video generation models like DALL.E, Stable-Diffusion and SORA. Though these models are necessary in many low-latency applications like…

计算机视觉与模式识别 · 计算机科学 2025-02-21 Vignesh Sundaresha

Task-oriented communication presents a promising approach to improve the communication efficiency of edge inference systems by optimizing learning-based modules to extract and transmit relevant task information. However, real-time…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Songjie Xie , Hengtao He , Shenghui Song , Jun Zhang , Khaled B. Letaief

In recent years, dual-target Cross-Domain Recommendation (CDR) has been proposed to capture comprehensive user preferences in order to ultimately enhance the recommendation accuracy in both data-richer and data-sparser domains…

信息检索 · 计算机科学 2025-05-23 Jiajie Zhu , Yan Wang , Feng Zhu , Zhu Sun

Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to…

Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Phillip Mueller , Jannik Wiese , Ioan Craciun , Lars Mikelsons

In recent years roboticists have achieved remarkable progress in solving increasingly general tasks on dexterous robotic hardware by leveraging high capacity Transformer network architectures and generative diffusion models. Unfortunately,…

机器人学 · 计算机科学 2024-10-15 Sudeep Dasari , Oier Mees , Sebastian Zhao , Mohan Kumar Srirama , Sergey Levine

In this paper, we propose a novel diffusion-decision transformer (D2T) architecture to optimize the beamforming strategies for intelligent reflecting surface (IRS)-assisted multiple-input single-output (MISO) communication systems. The…

信号处理 · 电气工程与系统科学 2024-07-01 Jie Zhang , Jun Li , Zhe Wang , Yu Han , Long Shi , Bin Cao