TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

FireRed-OCR

It targets “structural hallucination” in complex documents using progressive training and format-constrained GRPO, and reports strong results on OmniDocBench v1.5 with a Qwen3-VL-based 2B model.
New Multimodal Gen 3
Released: February 27, 2026

Overview

FireRed-OCR is a framework that specializes large vision-language models into pixel-precise structural document parsing models.

About FireRedTeam

View Company Profile

Tools using FireRed-OCR

No tools found for this model yet.

Last updated: March 2, 2026
0 AIs selected
Clear selection
#
Name
Task