Yanyu Li

16

Papers

59

Total Citations

Papers (16)

Improving the Diffusability of Autoencoders

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

Efficient Training with Denoised Neural Weights

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

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

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

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

Rethinking Vision Transformers for MobileNet Size and Speed

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

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

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

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

TextCraftor: Your Text Encoder Can be Image Quality Controller

EfficientFormer: Vision Transformers at MobileNet Speed

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

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