view article Article Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model CohereLabs • Aug 12 • 40
Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards Paper • 2609.03181 • Published 17 days ago • 7
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 17 days ago • 399
OCR: Leaderboards Collection Where OCR models are actually scored. Benchmark datasets with results tables first, then per-language leaderboard Spaces. Ordered by likes. • 7 items • Updated 2 days ago • 3
view article Article Generating Synthetic Training Data with Dask on Hugging Face Jobs Hanno-Labs • 3 days ago • 3
RelateAnything Collection Real-time open-vocabulary relation prediction from any regions: the released relation prediction models. • 4 items • Updated 4 days ago • 4
BuzzASR: 102 Monolingual ASR Models Collection Language-specialized Whisper-large-v3 fine-tunes, one per FLEURS language. Findings of EMNLP 2026. arxiv.org/abs/2609.09554 • 103 items • Updated 5 days ago • 1
BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models Paper • 2609.09554 • Published 10 days ago • 1
view article Article Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL +2 aminediroHF, qgallouedec, kashif, sergiopaniego • 9 days ago • 36
view article Article mmBERT: ModernBERT goes Multilingual +4 mmarone, orionweller, will-fleshman, eugene-yang, dlawrie, vandurme • Sep 9, 2025 • 155
view article Article IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license ibm-research • 9 days ago • 58
FrogNano: Training a 4B Coding Agent via Online Task Synthesis Paper • 2609.07925 • Published 12 days ago • 2
OCR: Documents Collection Roughly ordered by recent releases, useful updates and current usage. Practical OCR and document parsing models. Reviewed September 2026. • 17 items • Updated 11 days ago • 1
OCR: Languages & scripts Collection OCR for particular languages and writing systems, from whole-page readers to dedicated text-line recognisers. • 10 items • Updated 11 days ago • 1
OCR: Handwriting & archives Collection Handwriting, historical print and manuscript recognition. Notes on languages, text-line segmentation and transcription conventions. • 10 items • Updated 11 days ago • 1
OCR on the Hub Collection Curated OCR models for documents, languages, handwriting and text in images. Browse five collections with short practical notes. • 5 items • Updated 2 days ago • 11
OCR: Text recognition & pipelines Collection Text-line and region recognisers, plus detection and recognition pipelines for documents, manga and text in photographs. • 6 items • Updated 11 days ago • 1
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published Jul 18 • 99