23 citations · 35 across the 9 of their papers we have counts for
10 papers
SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
Dongting Hu, Aarush Gupta, Magzhan Gabidolla +12
Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and mem…
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
Dongting Hu, Jierun Chen, Xijie Huang +16
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to…
Efficient Training with Denoised Neural Weights
Yifan Gong, Zheng Zhan, Yanyu Li +6
Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challengin…
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
Yang Sui, Yanyu Li, Anil Kag +7
Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content. However, these models contain a…
TextCraftor: Your Text Encoder Can be Image Quality Controller
Yanyu Li, Xian Liu, Anil Kag +6
Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have revolutionized the field of content generation, enabling significant advancements in areas like image…
EGAN: Efficient Training of Efficient GANs for Image-to-Image Translation
Yifan Gong, Zheng Zhan, Qing Jin +8
One highly promising direction for enabling flexible real-time on-device image editing is utilizing data distillation by leveraging large-scale text-to-image diffusion models to ge…
Model compression as constrained optimization, with application to neural nets. Part V: combining compressions
Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. One fundamenta…
A flexible, extensible software framework for model compression based on the LC algorithm
Yerlan Idelbayev, Miguel Á. Carreira-Perpiñán
We propose a software framework based on the ideas of the Learning-Compression (LC) algorithm, that allows a user to compress a neural network or other machine learning model using…
Structured Multi-Hashing for Model Compression
Elad Eban, Yair Movshovitz-Attias, Hao Wu +4
Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models…
Model compression as constrained optimization, with application to neural nets. Part II: quantization
Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev
We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with entries…