Yanyu Li

26 papers · 2021–2025 · 9 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (5) 🗺️ Taxonomy Completionist (27) 🏆 Grand Slam 👑 Triple Crown 🤝 Dynamic Duo (20) 🔬 Deep Specialist (15) 💎 Century Club (26) 🔥 Unstoppable (5) 🗃️ Keyword Collector (82) ⚡ Prolific Year (7)

Conferences

CVPR (5) NIPS (5) AAAI (4) ECCV (3) IJCAI (3) ICCV (2) ICML (2) EMNLP (1) ICLR (1)

Top co-authors

Yanzhi Wang (20) Sergey Tulyakov (13) Jian Ren (12) Geng Yuan (9) Wei Niu (8) Bin Ren (7) Pu Zhao (7) Ju Hu (6) Xue Lin (6) Anil Kag (5)

Keywords

model compression (10) diffusion model (6) mobile inference (5) edge computing (5) neural architecture search (5) efficient computing (4) vision transformer (4) inference acceleration (3) video generation (3) structured pruning (3) latency optimization (3) image generation (3) text-to-image generation (3) neural network optimization (3) model acceleration (3) knowledge distillation (2) neural network pruning (2) weight quantization (2) mobile deployment (2) object detection (2)

Papers

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training CVPR 2025

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device CVPR 2025

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers AAAI 2025

Improving the Diffusability of Autoencoders ICML 2025

Predictive Modeling of Human Developers’ Evaluative Judgment of Generated Code as a Decision Process EMNLP 2025

FasterVD: On Acceleration of Video Diffusion Models IJCAI 2024

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model NIPS 2024

SF-V: Single Forward Video Generation Model NIPS 2024

TextCraftor: Your Text Encoder Can be Image Quality Controller CVPR 2024

Efficient Training with Denoised Neural Weights ECCV 2024

HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion ICLR 2024

E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation ICML 2024

Towards Real-Time Segmentation on the Edge AAAI 2023

Rethinking Vision Transformers for MobileNet Size and Speed ICCV 2023

Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge CVPR 2023

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds NIPS 2023

Real-Time Portrait Stylization on the Edge IJCAI 2022

EfficientFormer: Vision Transformers at MobileNet Speed NIPS 2022

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training NIPS 2022

You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding ECCV 2022

Compiler-Aware Neural Architecture Search for On-Mobile Real-Time Super-Resolution ECCV 2022

Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization IJCAI 2022

RMSMP: A Novel Deep Neural Network Quantization Framework With Row-Wise Mixed Schemes and Multiple Precisions ICCV 2021

NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration CVPR 2021

YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design AAAI 2021

A Compression-Compilation Co-Design Framework Towards Real-Time Object Detection on Mobile Devices AAAI 2021