Unlimited OCR Works
Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pag…
Hugging Face · Daily Papers
·Youyang Yin, Huanhuan Liu
·
·▲ 9 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Youyang Yin, Huanhuan Liu, YY, Qunyi Xie, Chaorun Liu, Shiqi Yang
- 9 upvotes da comunidade
- Temas: end-to-end OCR, large language model, decoder, KV cache, attention layers, Reference Sliding Window Attention
Resumo
Resumo original (em inglês), extraído do paper:
Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.
// relacionados
Leia também
Blog
How Businesses Are Building Specialized AI They Can Trust
Blog
Fika Jobs raises $4M to build a video-first hiring platform where AI agents interview candidates
Blog
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
Blog