Tianhong Li
- Papers
- 8
Cite
Notes
Only stored in your browser.
8papers
Authored papers
8Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
arXiv 2026
DREAM: Where Visual Understanding Meets Text-to-Image Generation
arXiv 2026
Latent Denoising Makes Good Visual Tokenizers
arXiv 2025
Fractal Generative Models
arXiv 2025
Back to Basics: Let Denoising Generative Models Denoise
arXiv 2025
Autoregressive Image Generation without Vector Quantization
arXiv 2024
Return of Unconditional Generation: A Self-supervised Representation Generation Method
arXiv 2023
MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
CVPR 2023 1
Affiliations
No known affiliations.
Frequent co-authors
10from 8 papers