Pu Zhao

14

Papers

672

Total Citations

Papers (14)

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Numerical Pruning for Efficient Autoregressive Models

InstructGIE: Towards Generalizable Image Editing

Sparse Learning for State Space Models on Mobile

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

On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method

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

LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval

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

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

Advancing Model Pruning via Bi-level Optimization