Xuefei Ning
- Papers
- 16
Cite
Notes
Only stored in your browser.
Authored papers
16Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
arXiv 2025
LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K
arXiv 2024
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
CVPR 2025 1
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models
ICCV 2025
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
arXiv 2024
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
arXiv 2024
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
arXiv 2024
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
arXiv 2024
CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
arXiv 2024
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
arXiv 2024
Decouple-Then-Merge: Towards Better Training for Diffusion Models
arXiv 2024
LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization
arXiv 2024
DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
arXiv 2024
MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression
arXiv 2024
Evaluating Quantized Large Language Models
arXiv 2024
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
arXiv 2023
Affiliations
Frequent co-authors
10from 16 papers