Yerlan Idelbayev
YOU?
Author Swipe
View article: SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training Open
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 address all of these challenges by developing an extremely …
View article: Efficient Training with Denoised Neural Weights
Efficient Training with Denoised Neural Weights Open
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 challenging and may require manual tuning, which can be time-consumin…
View article: BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model Open
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 huge number of parameters, resulting in a significantly lar…
View article: TextCraftor: Your Text Encoder Can be Image Quality Controller
TextCraftor: Your Text Encoder Can be Image Quality Controller Open
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 editing and video synthesis. Despite their formidable capab…
View article: E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation Open
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 generate paired datasets used for training generative adversa…
View article: LC: A Flexible, Extensible Open-Source Toolkit for Model Compression
LC: A Flexible, Extensible Open-Source Toolkit for Model Compression Open
The continued increase in memory, runtime and energy consumption of deployed machine learning models on one side, and the trend to miniaturize intelligent devices and sensors on the other side, imply that model compression will remain a cr…
View article: Model compression as constrained optimization, with application to neural nets. Part V: combining compressions
Model compression as constrained optimization, with application to neural nets. Part V: combining compressions Open
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. One fundamental question is: what types of compression work better for a …
View article: Structured Multi-Hashing for Model Compression
Structured Multi-Hashing for Model Compression Open
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 are held in memory. Model compression methods address this…
View article: A flexible, extensible software framework for model compression based on the LC algorithm
A flexible, extensible software framework for model compression based on the LC algorithm Open
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 different compression schemes with minimal effort. Current…
View article: A flexible, extensible software framework for model compression based on\n the LC algorithm
A flexible, extensible software framework for model compression based on\n the LC algorithm Open
We propose a software framework based on the ideas of the\nLearning-Compression (LC) algorithm, that allows a user to compress a neural\nnetwork or other machine learning model using different compression schemes\nwith minimal effort. Curr…
View article: Model compression as constrained optimization, with application to neural nets. Part II: quantization
Model compression as constrained optimization, with application to neural nets. Part II: quantization Open
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 $K$ entries so that the training loss of the quantized net is minimal. …