Xuefeng Xiao

20

Papers

272

Total Citations

Papers (20)

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

AffineQuant: Affine Transformation Quantization for Large Language Models

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

ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models

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

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

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

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

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

ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer

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

RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories

polybasic Speculative Decoding Through a Theoretical Perspective

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

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

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Online Multi-Granularity Distillation for GAN Compression

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

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

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