影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
74.06/100
前 2%
全站排名 #1,301
发表论文13 篇
平均评分
年均产出6.5 篇/年
Muyang Li
研究方向
Efficient Deep Learning · Generative Models · Machine Learning System
10
LongLive: Real-time Interactive Long Video Generation
ICLR 2026Poster
21
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
ICLR 2026Oral
11
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
ICLR 2026Rejected
11
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
ICLR 2026Rejected
16
MedQuanBench: Quantization-Aware Analysis for Efficient Medical Imaging Models
ICLR 2026Rejected
28
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers
ICLR 2025Oral
13
Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models
NeurIPS 2025Spotlight
三作27
SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
ICLR 2025Spotlight
一作18
Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation
NeurIPS 2025Poster
二作27
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
NeurIPS 2025Spotlight
12
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
ICML 2025Poster
19
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
ICLR 2025Poster
10
Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
ICML 2025Poster