Wei Niu

30 papers · 2020–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (42) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (8) 🏃 Academic Marathon (5) 🐝 Cross-Pollinator (11) 🤝 Dynamic Duo (23) 🔬 Deep Specialist (20) 🧬 Topic Evolution 🏆 Keyword Champion (7) 🗃️ Keyword Collector (105) 🔥 Unstoppable (6) 💎 Century Club (30) ⚡ Prolific Year (5)

Conferences

AAAI (7) CVPR (6) NIPS (5) ECCV (4) IJCAI (4) ICLR (2) ICCV (1) NAACL (1)

Top co-authors

Yanzhi Wang (23) Bin Ren (19) Pu Zhao (13) Geng Yuan (13) Xue Lin (10) Xuan Shen (9) Zheng Zhan (9) Yanyu Li (8) Zhenglun Kong (8) Xiaolong Ma (8)

Research topics

Keywords

model compression (17) real-time inference (7) mobile inference (7) edge computing (7) neural network optimization (6) neural network pruning (5) efficient computing (5) structured pruning (4) vision transformer (4) model pruning (4) neural architecture search (4) compiler optimization (4) mobile deployment (3) weight pruning (3) model acceleration (2) object detection (2) sparse training (2) deep neural network (2) memory efficiency (2) semantic segmentation (2)

Papers

Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings NAACL 2025

Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment AAAI 2025

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

AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction CVPR 2025

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge CVPR 2025

GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting CVPR 2025

Sparse Learning for State Space Models on Mobile ICLR 2025

Exploring Token Pruning in Vision State Space Models NIPS 2024

Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design ECCV 2024

NeurRev: Train Better Sparse Neural Network Practically via Neuron Revitalization ICLR 2024

Fast and Memory-Efficient Video Diffusion Using Streamlined Inference NIPS 2024

Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices NIPS 2024

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

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting CVPR 2023

Towards Real-Time Segmentation on the Edge AAAI 2023

SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning ECCV 2022

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

Real-Time Portrait Stylization on the Edge IJCAI 2022

SparCL: Sparse Continual Learning on the Edge NIPS 2022

RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices AAAI 2021

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

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge NIPS 2021

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

A Compression-Compilation Framework for On-mobile Real-time BERT Applications IJCAI 2021

Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices IJCAI 2021

Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search ICCV 2021

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

Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization IJCAI 2020

PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-Time Execution on Mobile Devices AAAI 2020

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices ECCV 2020