Yanyu Li

papers

1,309

total citations

papers (16)

Compiler-Aware Neural Architecture Search for On-Mobile Real-Time Super-Resolution

ECCV 2022arXiv

citations

NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration

CVPR 2021arXiv

citations

TextCraftor: Your Text Encoder Can be Image Quality Controller

CVPR 2024arXiv

citations

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device

CVPR 2025arXiv

citations

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

NEURIPS 2022arXiv

citations

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

CVPR 2025arXiv

citations

RMSMP: A Novel Deep Neural Network Quantization Framework With Row-Wise Mixed Schemes and Multiple Precisions

ICCV 2021arXiv

citations

Efficient Training with Denoised Neural Weights

ECCV 2024arXiv

citations

You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding

ECCV 2022

citations

Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge

CVPR 2023

citations

E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation

ICML 2024arXiv

citations

Yanyu Li

papers (16)

EfficientFormer: Vision Transformers at MobileNet Speed

Rethinking Vision Transformers for MobileNet Size and Speed

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Improving the Diffusability of Autoencoders

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Compiler-Aware Neural Architecture Search for On-Mobile Real-Time Super-Resolution

NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration

TextCraftor: Your Text Encoder Can be Image Quality Controller

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

RMSMP: A Novel Deep Neural Network Quantization Framework With Row-Wise Mixed Schemes and Multiple Precisions

Efficient Training with Denoised Neural Weights

You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding

Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge

E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation

papers (16)

EfficientFormer: Vision Transformers at MobileNet Speed

Rethinking Vision Transformers for MobileNet Size and Speed

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Improving the Diffusability of Autoencoders

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Compiler-Aware Neural Architecture Search for On-Mobile Real-Time Super-Resolution

NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration

TextCraftor: Your Text Encoder Can be Image Quality Controller

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

RMSMP: A Novel Deep Neural Network Quantization Framework With Row-Wise Mixed Schemes and Multiple Precisions

Efficient Training with Denoised Neural Weights

You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding

Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge

E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation