Xuefei Ning

9

Papers

75

Total Citations

Papers (9)

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization

FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models

MBQ: Modality-Balanced Quantization for Large Vision-Language Models

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning

ProReflow: Progressive Reflow with Decomposed Velocity

Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning

FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models

Evaluating Quantized Large Language Models