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
Back to Basics: Let Denoising Generative Models Denoise
arXiv 2025
Latent Denoising Makes Good Visual Tokenizers
arXiv 2025
Fractal Generative Models
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