Yerlan Idelbayev

Computer Science · Physical Sciences

6h-index513citations28works0.52yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Neural Networks and Applications(9), Advanced Neural Network Applications(6), Generative Adversarial Networks and Image Synthesis(5), Sparse and Compressive Sensing Techniques(4), Medical Image Segmentation Techniques(3)

Publications28 total

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
arXiv (Cornell University)·2026Open Access
SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
arXiv (Cornell University)·2026Open Access
SnapGen: Taming High-Resolution Text-To-Image Models for Mobile Devices with Efficient Architectures and Training
2025
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
arXiv (Cornell University)·2024Open Access
Efficient Training with Denoised Neural Weights
Lecture notes in computer science·2024
Efficient Training with Denoised Neural Weights
arXiv (Cornell University)·2024Open Access
TextCraftor: Your Text Encoder can be Image Quality Controller
2024· 4 cited
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
arXiv (Cornell University)·2024· 1 citedOpen Access
TextCraftor: Your Text Encoder Can be Image Quality Controller
arXiv (Cornell University)·2024Open Access
E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
arXiv (Cornell University)·2024· 1 citedOpen Access
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
2024
Exploring the Effect of ℓ<sub>0</sub>/ℓ<sub>2</sub> Regularization in Neural Network Pruning using the LC Toolkit
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)·2022· 3 cited
LC: A Flexible, Extensible Open-Source Toolkit for Model Compression
2021· 8 citedOpen Access
Beyond Flops In Low-Rank Compression Of Neural Networks: Optimizing Device-Specific Inference Runtime
2021· 6 cited
An Empirical Comparison of Quantization, Pruning and Low-rank Neural Network Compression using the LC Toolkit
2021· 1 cited
Model compression as constrained optimization, with application to neural nets. Part V: combining compressions
arXiv (Cornell University)·2021· 5 citedOpen Access
Optimal Quantization using Scaled Codebook
2021· 2 cited
Optimal Selection of Matrix Shape and Decomposition Scheme for Neural Network Compression
2021· 5 cited
Neural Network Compression via Additive Combination of Reshaped, Low-Rank Matrices
2021· 5 cited
More General and Effective Model Compression via an Additive Combination of Compressions
Lecture notes in computer science·2021· 9 cited
page 1 of 2Next →

Frequent Co-authors

Miguel Á. Carreira-Perpiñán(15), Yanyu Li(9), Sergey Tulyakov(6), Anil Kag(5), Yanzhi Wang(5), Hu Ju(4), Dhritiman Sagar(4), Jun‐Li Cao(4), Dongting Hu(4), Dishani Lahiri(4), Jian Ren(3), Yifan Gong(3), Zheng Zhan(3), Andrey Zharkov(3), Kfir Aberman(3), Sergey Tulyakov(3), Jian Ren(3), Anil Kag(3), Chen Zhang(2), Nicholas Roberts(2)