News for hackers. Stuff that matters.

A comment on Replace OCR with Vision Language Models. Parent comment

Re:Replace OCR with Vision Language Models by the8472 on Thursday February 27, 2025 @02:40PM (#43197689)
Shouldn't confidence be available at the sampler level and also be conditional on the vision input, not just the next-token prediction?
[ Parent | on HN ]

There are no comments on this comment yet.