Comment by 0x457
16 hours ago
Would it be helpful if LLM creates bounding boxes for "traditional" OCR to work on? I.e. allowing extraction of information of arbitrary PDF as if it was a "particular pdf"
16 hours ago
Would it be helpful if LLM creates bounding boxes for "traditional" OCR to work on? I.e. allowing extraction of information of arbitrary PDF as if it was a "particular pdf"
No comments yet
Contribute on Hacker News ↗