GEAR: Guided End-to-End AutoRegression for Image Synthesis
GEAR trains a vector-quantized tokenizer and autoregressive generator jointly end-to-end using representation alignment, overcoming non-differentiability issues through a dual read…
Hugging Face · Daily Papers
·Bin Lin, Zheyuan Liu
·
·▲ 28 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Bin Lin, Zheyuan Liu, Chenguo Lin, Sixiang Chen, Yunyang Ge, Yunlong Lin
- 28 upvotes da comunidade
- Temas: vector-quantized, autoregressive, representation alignment, straight-through estimator, codebook assignment, next-token prediction
Resumo
Resumo original (em inglês), extraído do paper:
GEAR trains a vector-quantized tokenizer and autoregressive generator jointly end-to-end using representation alignment, overcoming non-differentiability issues through a dual read-out approach that improves convergence speed and feature quality.Onde ler
// relacionados
Leia também
Blog
Ashton Kutcher leaving Sound Ventures to launch new VC firm with Morgan Beller
Blog
After spooking Trump into safety testing, Anthropic AI models get global release
Blog
Why Solve It Twice? Hierarchical Accumulation of Skills for Transfer-Efficient ML Engineering
Blog