English
Related papers

Related papers: Scaling Laws For Diffusion Transformers

200 papers

Dataset distillation (DD) aims to construct compact synthetic datasets that allow models to achieve comparable performance to full-data training while substantially reducing storage and computation. Despite rapid empirical progress, its…

Machine Learning · Computer Science 2025-12-11 Zhengquan Luo , Zhiqiang Xu

In this work, we provide a sharp theory of scaling laws for two-layer neural networks trained on a class of hierarchical multi-index targets, in a genuinely representation-limited regime. We derive exact information-theoretic scaling laws…

Machine Learning · Statistics 2026-02-06 Leonardo Defilippis , Florent Krzakala , Bruno Loureiro , Antoine Maillard

Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most existing diffusion codecs employ U-Net architectures, where…

Image and Video Processing · Electrical Eng. & Systems 2026-03-16 Junqi Shi , Ming Lu , Xingchen Li , Anle Ke , Ruiqi Zhang , Zhan Ma

Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Yongsheng Yu , Wei Xiong , Weili Nie , Yichen Sheng , Shiqiu Liu , Jiebo Luo

Scaling laws, a defining feature of deep learning, reveal a striking power-law improvement in model performance with increasing dataset and model size. Yet, their mathematical origins, especially the scaling exponent, have remained elusive.…

Machine Learning · Computer Science 2026-03-24 Yuda Bi , Vince D Calhoun

Diffusion models produce high quality images but inference is costly due to many denoising steps and heavy matrix operations. We present DiffPro, a post-training, hardware-faithful framework that works with the exact integer kernels used in…

Machine Learning · Computer Science 2025-11-17 Farhana Amin , Sabiha Afroz , Kanchon Gharami , Mona Moghadampanah , Dimitrios S. Nikolopoulos

Scaling laws for language models have often focused on finding the optimal model size and token count for training from scratch. However, achieving this optimal balance requires significant compute resources due to the extensive data…

Computation and Language · Computer Science 2025-04-01 Roseval Malaquias Junior , Ramon Pires , Thales Sales Almeida , Kenzo Sakiyama , Roseli A. F. Romero , Rodrigo Nogueira

While scaling laws for Large Language Models (LLMs) traditionally focus on proxy metrics like pretraining loss, predicting downstream task performance has been considered unreliable. This paper challenges that view by proposing a direct…

Machine Learning · Computer Science 2025-12-10 Jakub Krajewski , Amitis Shidani , Dan Busbridge , Sam Wiseman , Jason Ramapuram

Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Hangyeol Lee , Hyojeong Lee , Joo-Young Kim

Diffusion models have become the dominant paradigm in text-to-image generation, and test-time scaling (TTS) improves sample quality by allocating additional computation at inference. Existing TTS methods, however, resample the entire image,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Qin Ren , Yufei Wang , Lanqing Guo , Wen Zhang , Zhiwen Fan , Chenyu You

In this paper, we investigate how to convert a pre-trained Diffusion Transformer (DiT) into a linear DiT, as its simplicity, parallelism, and efficiency for image generation. Through detailed exploration, we offer a suite of ready-to-use…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Jiahao Wang , Ning Kang , Lewei Yao , Mengzhao Chen , Chengyue Wu , Songyang Zhang , Shuchen Xue , Yong Liu , Taiqiang Wu , Xihui Liu , Kaipeng Zhang , Shifeng Zhang , Wenqi Shao , Zhenguo Li , Ping Luo

Deep learning has recently revealed the existence of scaling laws, demonstrating that model performance follows predictable trends based on dataset and model sizes. Inspired by these findings and fascinating phenomena emerging in the…

Machine Learning · Statistics 2026-02-10 Mattia Rosso , Simone Rossi , Giulio Franzese , Markus Heinonen , Maurizio Filippone

The Text-to-Video (T2V) model aims to generate dynamic and expressive videos from textual prompts. The generation pipeline typically involves multiple modules, such as language encoder, Diffusion Transformer (DiT), and Variational…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-17 Heyang Huang , Cunchen Hu , Jiaqi Zhu , Ziyuan Gao , Liangliang Xu , Yizhou Shan , Yungang Bao , Sun Ninghui , Tianwei Zhang , Sa Wang

The geometry of fracture patterns in a dilute elastic network is explored using molecular dynamics simulation. The network in two dimensions is subjected to a uniform strain which drives the fracture to develop by the growth and coalescence…

Condensed Matter · Physics 2015-06-25 P. Ray , G. Date

Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to extracting maximum value from limited data. The widely adopted Chinchilla scaling law…

Machine Learning · Computer Science 2026-05-05 Justin Lovelace , Christian Belardi , Srivatsa Kundurthy , Shriya Sudhakar , Kilian Q. Weinberger

Time series forecasting plays a critical role in decision-making processes across diverse fields including meteorology, traffic, electricity, economics, finance, and so on. Especially, predicting returns on financial instruments is a…

Machine Learning · Computer Science 2025-09-08 Yuki Takemoto

Recent advanced diffusion methods typically derive strong generative priors by scaling diffusion transformers. However, scaling fails to generalize when adapted for real-time compression scenarios that demand lightweight models. In this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Zhaoyang Jia , Naifu Xue , Zihan Zheng , Jiahao Li , Bin Li , Xiaoyi Zhang , Zongyu Guo , Yuan Zhang , Houqiang Li , Yan Lu

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse attention - enhance inference speed but typically rely on a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Wangbo Zhao , Yizeng Han , Zhiwei Tang , Jiasheng Tang , Pengfei Zhou , Kai Wang , Bohan Zhuang , Zhangyang Wang , Fan Wang , Yang You

Diffusion models achieve superior performance in image generation tasks. However, it incurs significant computation overheads due to its iterative structure. To address these overheads, we analyze this iterative structure and observe that…

Hardware Architecture · Computer Science 2025-01-22 Sungbin Kim , Hyunwuk Lee , Wonho Cho , Mincheol Park , Won Woo Ro

Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks. To alleviate this inefficiency, we propose \textbf{FastCache}, a…

Machine Learning · Computer Science 2026-03-30 Dong Liu , Yanxuan Yu , Jiayi Zhang , Yifan Li , Ben Lengerich , Ying Nian Wu