Xuefeng Xiao

papers

796

total citations

papers (22)

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

ECCV 2024arXiv

153

citations

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

CVPR 2023arXiv

124

citations

Diffusion Adversarial Post-Training for One-Step Video Generation

ICML 2025arXiv

citations

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

ICCV 2023arXiv

citations

ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer

ECCV 2022arXiv

citations

Online Multi-Granularity Distillation for GAN Compression

ICCV 2021arXiv

citations

AffineQuant: Affine Transformation Quantization for Large Language Models

ICLR 2024arXiv

citations

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme

NEURIPS 2021arXiv

citations

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

CVPR 2023arXiv

citations

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

ICCV 2025arXiv

citations

RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories

CVPR 2025arXiv

citations

Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM

ICCV 2025arXiv

citations

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

ECCV 2024arXiv

citations

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model

ICLR 2025arXiv

citations

Multi-Granularity Distillation Scheme towards Lightweight Semi-Supervised Semantic Segmentation

ECCV 2022arXiv

citations

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

ICCV 2025arXiv

citations

UGC: Unified GAN Compression for Efficient Image-to-Image Translation

ICCV 2023arXiv

citations

Outlier-aware Slicing for Post-Training Quantization in Vision Transformer

ICML 2024

citations

polybasic Speculative Decoding Through a Theoretical Perspective

ICML 2025arXiv

citations

Xuefeng Xiao

papers (22)

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Diffusion Adversarial Post-Training for One-Step Video Generation

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer

Online Multi-Granularity Distillation for GAN Compression

AffineQuant: Affine Transformation Quantization for Large Language Models

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme

Training-free and Adaptive Sparse Attention for Efficient Long Video Generation

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories

Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model

Multi-Granularity Distillation Scheme towards Lightweight Semi-Supervised Semantic Segmentation

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

UGC: Unified GAN Compression for Efficient Image-to-Image Translation

Outlier-aware Slicing for Post-Training Quantization in Vision Transformer

polybasic Speculative Decoding Through a Theoretical Perspective

papers (22)

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Diffusion Adversarial Post-Training for One-Step Video Generation

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer

Online Multi-Granularity Distillation for GAN Compression

AffineQuant: Affine Transformation Quantization for Large Language Models

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme

Training-free and Adaptive Sparse Attention for Efficient Long Video Generation

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories

Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model

Multi-Granularity Distillation Scheme towards Lightweight Semi-Supervised Semantic Segmentation

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

UGC: Unified GAN Compression for Efficient Image-to-Image Translation

Outlier-aware Slicing for Post-Training Quantization in Vision Transformer

polybasic Speculative Decoding Through a Theoretical Perspective