0

Xuefei Ning

Papers
16

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
16papers

Authored papers

16

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

arXiv 2025

2025

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

arXiv 2024

2024

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

CVPR 2025 1

2024

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

ICCV 2025

2024

Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study

arXiv 2024

2024

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

arXiv 2024

2024

Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding

arXiv 2024

2024

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

arXiv 2024

2024

CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios

arXiv 2024

2024

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

arXiv 2024

2024

Decouple-Then-Merge: Towards Better Training for Diffusion Models

arXiv 2024

2024

LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization

arXiv 2024

2024

DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis

arXiv 2024

2024

MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression

arXiv 2024

2024

Evaluating Quantized Large Language Models

arXiv 2024

2024

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

arXiv 2023

2023

Affiliations

No known affiliations.

Frequent co-authors

10

from 16 papers