中文
相关论文

相关论文: HiCache: A Plug-in Scaled-Hermite Upgrade for Tayl…

200 篇论文

We introduce Home-made Diffusion Model (HDM), an efficient yet powerful text-to-image diffusion model optimized for training (and inferring) on consumer-grade hardware. HDM achieves competitive 1024x1024 generation quality while maintaining…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Shih-Ying Yeh

Recent advances in diffusion models have demonstrated impressive capability in generating high-quality images for simple prompts. However, when confronted with complex prompts involving multiple objects and hierarchical structures, existing…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Hongji Yang , Yucheng Zhou , Wencheng Han , Runzhou Tao , Zhongying Qiu , Jianfei Yang , Jianbing Shen

Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial role in ensuring generation quality. However, their…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Minghao Fu , Guo-Hua Wang , Liangfu Cao , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang

Data-intensive applications often require exploratory analysis of large datasets. If analysis is performed on distributed resources, data locality can be crucial to high throughput and performance. We propose a "data diffusion" approach…

分布式、并行与集群计算 · 计算机科学 2016-11-17 Ioan Raicu , Yong Zhao , Ian Foster , Alex Szalay

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive…

计算机视觉与模式识别 · 计算机科学 2025-09-24 Shuning Chang , Pichao Wang , Jiasheng Tang , Fan Wang , Yi Yang

Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application suffers from inherent dynamic feature instability, leading…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Guanjie Chen , Xinyu Zhao , Yucheng Zhou , Xiaoye Qu , Tianlong Chen , Yu Cheng

Deep image restoration models aim to learn a mapping from degraded image space to natural image space. However, they face several critical challenges: removing degradation, generating realistic details, and ensuring pixel-level consistency.…

计算机视觉与模式识别 · 计算机科学 2025-07-31 Xinqi Lin , Fanghua Yu , Jinfan Hu , Zhiyuan You , Wu Shi , Jimmy S. Ren , Jinjin Gu , Chao Dong

Although Diffusion Transformer (DiT) has emerged as a predominant architecture for image and video generation, its iterative denoising process results in slow inference, which hinders broader applicability and development. Caching-based…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Tong Shao , Yusen Fu , Guoying Sun , Jingde Kong , Zhuotao Tian , Jingyong Su

Coarse-to-fine autoregressive modeling has recently shown strong promise for visuomotor policy learning, combining the inference efficiency of autoregressive methods with the global trajectory coherence of diffusion-based policies. However,…

机器人学 · 计算机科学 2026-03-31 Daichi Yashima , Koki Seno , Shuhei Kurita , Yusuke Oda , Komei Sugiura

Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…

计算机视觉与模式识别 · 计算机科学 2026-02-26 Euisoo Jung , Byunghyun Kim , Hyunjin Kim , Seonghye Cho , Jae-Gil Lee

Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Kinam Kim , Junha Hyung , Jaegul Choo

The inference latency of diffusion models remains a critical barrier to their real-time application. While trajectory-based and distribution-based step distillation methods offer solutions, they present a fundamental trade-off.…

计算机视觉与模式识别 · 计算机科学 2025-11-13 Hanbo Cheng , Peng Wang , Kaixiang Lei , Qi Li , Zhen Zou , Pengfei Hu , Jun Du

Given an input video of a person and a new garment, the objective of this paper is to synthesize a new video where the person is wearing the specified garment while maintaining spatiotemporal consistency. Although significant advances have…

计算机视觉与模式识别 · 计算机科学 2024-12-19 Hung Nguyen , Quang Qui-Vinh Nguyen , Khoi Nguyen , Rang Nguyen

In cost-sensitive deployments, RAID arrays may combine SSDs with different performance levels. Such heterogeneity arises when aging SSDs degrade yet remain usable, or when failed drives are replaced with new devices of explicitly better…

操作系统 · 计算机科学 2026-04-03 Jialin Liu , Liang Shi , Dingcui Yu

The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se presents a critical hurdle to efficiency. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2024-04-10 Xingyi Yang , Xinchao Wang

Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access. To avoid code-intrusion…

分布式、并行与集群计算 · 计算机科学 2025-06-17 Tianze Wang , Yifei Liu , Chen Chen , Pengfei Zuo , Jiawei Zhang , Qizhen Weng , Yin Chen , Zhenhua Han , Jieru Zhao , Quan Chen , Minyi Guo

Diffusion Transformers (DiTs) have achieved state-of-the-art video generation quality, but they incur immense computational cost because standard inference applies the same number of denoising steps uniformly to every token in the sequence.…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Ernie Chu , Vishal M. Patel

Recommendation systems face the challenge of balancing accuracy and diversity, as traditional collaborative filtering (CF) and network-based diffusion algorithms exhibit complementary limitations. While item-based CF (ItemCF) enhances…

信息检索 · 计算机科学 2025-03-04 Yu Peng , Ya-Hui An

Text-to-image generation employing diffusion models has attained significant popularity due to its capability to produce high-quality images that adhere to textual prompts. However, the integration of diffusion models faces critical…

网络与互联网体系结构 · 计算机科学 2025-12-05 Hanshuai Cui , Zhiqing Tang , Zhi Yao , Weijia Jia , Wei Zhao

Real-time world simulation is becoming a key infrastructure for scalable evaluation and online reinforcement learning of autonomous driving systems. Recent driving world models built on autoregressive video diffusion achieve high-fidelity,…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Yixiao Zeng , Jianlei Zheng , Chaoda Zheng , Shijia Chen , Mingdian Liu , Tongping Liu , Tengwei Luo , Yu Zhang , Boyang Wang , Linkun Xu , Siyuan Lu , Bo Tian , Xianming Liu
‹ 上一页 1 8 9 10 下一页 ›