Zhihang Yuan

papers

820

total citations

papers (16)

Post-Training Quantization on Diffusion Models

CVPR 2023arXiv

270

citations

PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization

ECCV 2022arXiv

201

citations

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

CVPR 2025arXiv

citations

MIM4DD: Mutual Information Maximization for Dataset Distillation

NEURIPS 2023arXiv

citations

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

NEURIPS 2025arXiv

citations

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance

ICML 2025arXiv

citations

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers

ICCV 2025arXiv

citations

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

ICML 2024arXiv

citations

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

ICCV 2025arXiv

citations

DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate

ICCV 2025

citations

S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

ECCV 2020

citations

PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram

CVPR 2025

citations

Zhihang Yuan

papers (16)

Post-Training Quantization on Diffusion Models

PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization

PD-Quant: Post-Training Quantization Based on Prediction Difference Metric

PB-LLM: Partially Binarized Large Language Models

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

Latency-aware Spatial-wise Dynamic Networks

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

MIM4DD: Mutual Information Maximization for Dataset Distillation

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate

S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram

papers (16)

Post-Training Quantization on Diffusion Models

PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization

PD-Quant: Post-Training Quantization Based on Prediction Difference Metric

PB-LLM: Partially Binarized Large Language Models

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

Latency-aware Spatial-wise Dynamic Networks

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

MIM4DD: Mutual Information Maximization for Dataset Distillation

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate

S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram