Mingxiao Li
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion
arXiv 2026
Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding
arXiv 2025
Step-Audio 2 Technical Report
arXiv 2025
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
arXiv 2025
DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
arXiv 2024
TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
arXiv 2024
SePPO: Semi-Policy Preference Optimization for Diffusion Alignment
arXiv 2024
Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
arXiv 2023
Elucidating the Exposure Bias in Diffusion Models
arXiv 2023
Affiliations
Frequent co-authors
10from 9 papers