A 32-token 1D image tokenizer, optimized at test time against CLIP or reconstruction losses, performs image editing, inpainting, and class-conditional generation without training a generative model.
Why are conditional generative models better than unconditional ones? In NeurIPS 2022 Workshop on Score-Based Methods, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Highly Compressed Tokenizer Can Generate Without Training
A 32-token 1D image tokenizer, optimized at test time against CLIP or reconstruction losses, performs image editing, inpainting, and class-conditional generation without training a generative model.