Unlimited OCR: One-shot long-horizon parsing
1–10 of 119 posts
Re: Unlimited OCR: One-shot long-horizon parsing
#2OCR has been solved long time ago with vision models. Solutions are consistent, reliable, and stable. What is the point of reinventing the wheel?
I would definitely understand post processing, like extracting data, answering question .. etc, but why re-doing the OCR engine itself?
Re: Unlimited OCR: One-shot long-horizon parsing
#3OCR has been solved long time ago with vision models. Solutions are consistent, reliable, and stable. What is the point of reinventing the wheel? I would definitely understand post processing, like extracting data, answering question .. etc, but why re-doing the OCR engine itself?
I haven't done much long-run OCR, so unsure of the current state, but it would seem they overcome this (from their paper):
"A widely held view is that employing a large language model (LLM) as the decoder allows the model to leverage the prior distribution of language, leading to improved OCR performance. However, the downside is equally evident: as the output sequence lengthens, the accumulated KV cache drives up memory consumption and progressively slows down generation."
Re: Unlimited OCR: One-shot long-horizon parsing
#4OCR has been solved long time ago with vision models. Solutions are consistent, reliable, and stable. What is the point of reinventing the wheel? I would definitely understand post processing, like extracting data, answering question .. etc, but why re-doing the OCR engine itself?
Cost, throughput, latency...
Re: Unlimited OCR: One-shot long-horizon parsing
#5Very interesting.
The way I understand this works is that the researchers found a clever architectural hack to stop AI from hoarding memory when reading long documents.
Normally, when an AI transcribes a 100 page PDF, it tries to remember every single word it has already ingested. This short-term memory (the KV cache) grows linearly O(N) until the model runs out of VRAM and crashes (or caps it) To avoid this, developers are forced to build janky code that chops PDFs into individual pages, processes them one by one, and glues the text back together.
Unlimited OCR uses Reference Sliding Window Attention (R-SWA) to split the AI's focus into two paths:
Global Reference: The AI keeps full, uncompromised sight of the original document image so it never loses context.
Local Generation: The AI restricts its memory of its own typed text to a tight, moving window (like the last 128 words) and safely forgets the rest.
Will be very interesting for local AI and can’t wait to see what the community builds and extends with it!
Re: Unlimited OCR: One-shot long-horizon parsing
#6OCR has been solved long time ago with vision models. Solutions are consistent, reliable, and stable. What is the point of reinventing the wheel? I would definitely understand post processing, like extracting data, answering question .. etc, but why re-doing the OCR engine itself?
Cost, throughput, latency...
Traditional OCR is faster, cheaper, and much more reliable than LLMs
Re: Unlimited OCR: One-shot long-horizon parsing
#7OCR has been solved long time ago with vision models. Solutions are consistent, reliable, and stable. What is the point of reinventing the wheel? I would definitely understand post processing, like extracting data, answering question .. etc, but why re-doing the OCR engine itself?
I guess, in theory, the prior distribution of language would allow for improved performance in some cases, especially where input quality is low.
Re: Unlimited OCR: One-shot long-horizon parsing
#8OCR has been solved long time ago with vision models. Solutions are consistent, reliable, and stable. What is the point of reinventing the wheel? I would definitely understand post processing, like extracting data, answering question .. etc, but why re-doing the OCR engine itself?
It absolutely hasn't been solved, it's just got pretty decent in recent years.
Re: Unlimited OCR: One-shot long-horizon parsing
#9OCR has been solved long time ago with vision models. Solutions are consistent, reliable, and stable. What is the point of reinventing the wheel? I would definitely understand post processing, like extracting data, answering question .. etc, but why re-doing the OCR engine itself?
OCR has definitely not "been solved long time ago", what are you talking about?
In your opinion, what is SOTA here?
Re: Unlimited OCR: One-shot long-horizon parsing
#10OCR has been solved long time ago with vision models. Solutions are consistent, reliable, and stable. What is the point of reinventing the wheel? I would definitely understand post processing, like extracting data, answering question .. etc, but why re-doing the OCR engine itself?
Detecting characters almost, layout no.