Decoder-only OCR Training Revisited with Meta's In-fusion, Better Annotations Planned
wightmanr · x · 2026-11-21
After Meta's in-fusion paper came out, a developer revived his old OCR project: after fixing old bugs, in-fusion proved a natural fit for the model architecture and works. As an alternative to the NaFlexViT encoder + text decoder setup, he trained a decoder-only variant (the original encoder relied on strong pretrained weights, hard to beat with short OCR training).
He trialed with the idl-wds dataset he and @molbap had uploaded to the pixparse project on HF, noting the annotation noise floor is readily apparent — good enough to establish reading capability but better annotations are needed. He's planning agent-driven reprocessing of pdfa-eng, pdfa-multi (never released due to annotation issues), and idl, and has asked Hugging Face for a quota bump as pixparse ran out of Hub space.
Related event: Developer Retrains Small OCR Models Inspired by Meta's In-Fusion Paper(2 posts)→
More from Research
- Riemann proof released as blog post and 8 zips, no listed author — eigenhector · 2026-11-21
- NeurIPS Paper Derives First Algorithm to Reconstruct Images from Disk Bispectrum Alone — ninamiolane · 2026-11-21
- Impetus Grants Appeals for Philanthropic Funding to Build the Biological Data AI Cures Need — shae_mcl · 2026-11-21
- Snorkel's binary-gated GRPO lifts Qwen3.8-27B from 31.9% to 40.7% on OpenAI's GDPval — ajratner · 2026-11-21
- Artificial Analysis Launches Search API Benchmark Covering 26 Products Across 14 Providers — ArtificialAnlys · 2026-11-21
- The 250,000-page Riemann proof claim: when computational verification outpaces human comprehension — SydSteyerhart · 2026-11-21