Geng Yuan

papers

991

total citations

papers (14)

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

NEURIPS 2021arXiv

citations

Teachers Do More Than Teach: Compressing Image-to-Image Models

CVPR 2021arXiv

citations

Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search

ICCV 2021arXiv

citations

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

CVPR 2021arXiv

citations

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

NEURIPS 2022arXiv

citations

Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment

AAAI 2025arXiv

citations

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

ECCV 2022

citations

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

ICML 2024

citations

SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning

ECCV 2022

citations

HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception

NEURIPS 2023

citations

PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile

NEURIPS 2023

citations

Geng Yuan

papers (14)

EfficientFormer: Vision Transformers at MobileNet Speed

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge

SparCL: Sparse Continual Learning on the Edge

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

Teachers Do More Than Teach: Compressing Image-to-Image Models

Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search

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

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

Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment

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

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning

HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception

PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile

papers (14)

EfficientFormer: Vision Transformers at MobileNet Speed

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge

SparCL: Sparse Continual Learning on the Edge

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

Teachers Do More Than Teach: Compressing Image-to-Image Models

Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search

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

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

Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment

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

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning

HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception

PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile