Wei Niu

15

Papers

39

Total Citations

Papers (15)

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

Sparse Learning for State Space Models on Mobile

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

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

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

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

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

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

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

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

GaussianSpa: An “Optimizing-Sparsifying” Simplification Framework for Compact and High-Quality 3D Gaussian Splatting

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

SparCL: Sparse Continual Learning on the Edge

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

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