Xuefei Ning

papers

785

total citations

papers (22)

A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS

ECCV 2020arXiv

116

citations

DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation

ECCV 2020arXiv

115

citations

FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning

CVPR 2022arXiv

111

citations

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

ECCV 2024arXiv

citations

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

COLM 2025arXiv

citations

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

ICCV 2025arXiv

citations

Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels

NEURIPS 2023arXiv

citations

Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

ICCV 2023arXiv

citations

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

CVPR 2025arXiv

citations

CLOSE: Curriculum Learning on the Sharing Extent towards Better One-Shot NAS

ECCV 2022arXiv

citations

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

CVPR 2024arXiv

citations

CodedVTR: Codebook-Based Sparse Voxel Transformer With Geometric Guidance

CVPR 2022arXiv

citations

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

ICLR 2025arXiv

citations

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

CVPR 2025arXiv

citations

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

NEURIPS 2025arXiv

citations

ProReflow: Progressive Reflow with Decomposed Velocity

CVPR 2025arXiv

citations

TA-GATES: An Encoding Scheme for Neural Network Architectures

NEURIPS 2022

citations

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

AAAI 2025

citations

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

NEURIPS 2025arXiv

citations

Xuefei Ning

papers (22)

A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS

DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation

FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning

Evaluating Efficient Performance Estimators of Neural Architectures

Evaluating Quantized Large Language Models

LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K

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

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

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

Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels

Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

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

CLOSE: Curriculum Learning on the Sharing Extent towards Better One-Shot NAS

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

CodedVTR: Codebook-Based Sparse Voxel Transformer With Geometric Guidance

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

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

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

ProReflow: Progressive Reflow with Decomposed Velocity

TA-GATES: An Encoding Scheme for Neural Network Architectures

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

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

papers (22)

A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS

DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation

FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning

Evaluating Efficient Performance Estimators of Neural Architectures

Evaluating Quantized Large Language Models

LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K

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

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

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

Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels

Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

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

CLOSE: Curriculum Learning on the Sharing Extent towards Better One-Shot NAS

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

CodedVTR: Codebook-Based Sparse Voxel Transformer With Geometric Guidance

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

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

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

ProReflow: Progressive Reflow with Decomposed Velocity

TA-GATES: An Encoding Scheme for Neural Network Architectures

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

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification