arXiv AI
Jul 16
OvisOCR2 Technical Report
arXiv:2607. 13639v1 Announce Type: cross Abstract: We introduce OvisOCR2, a 0.
OvisOCR3 Technical Report
Related stories
arXiv AI
Sep 30
PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence
arXiv:2609.37712v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) is evolving from plain-text transcription toward general visual intelligence, requiring models to recognize, loca...
arXiv Computer Vision
Sep 30
Xiaomi-OCR-0 Technical Report
arXiv:2609.36136v1 Announce Type: new Abstract: Compact OCR-specific vision-language models achieve strong document parsing performance, but often rely on costly supervision and focus primarily on vi...
Hugging Face Trending Papers
Jul 6
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
We present HunyuanOCR-1. 5, a lightweight end-to-end OCR-specialized vision-language model.
arXiv Computer Vision
Sep 18
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
HunyuanOCR-1.5 is a lightweight, end‑to‑end OCR‑specialized vision‑language model that unifies document parsing, text spotting, information extraction, text‑image translation, and multi‑image document understanding. It builds on the HunyuanOCR‑1.0 architecture, improving efficiency with DFlash‑based OCR decoding for faster inference (6.37× Transformer speedup, 2.14× under vLLM) and enhancing capability through an Agentic Data Flow system that autonomously constructs high‑quality training data for long‑tail OCR tasks. The model achieves top‑tier performance on OmniDocBench v1.6 and sets new milestones in ancient‑script OCR, chart/table parsing, multilingual parsing, and hallucination evaluation, while remaining lightweight for deployment.
Hugging Face Trending Papers
Sep 15
Tables Decoded: DELTA for Structure, TARQA for Understanding
Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rel...
arXiv AI
Sep 4
How Far Can Synthetic Data Take Thai OCR?
The paper explores how synthetic data can be used to train a Thai OCR model without real OCR labels. By systematically varying factors such as typeface diversity, page structure, and handwriting glyphs, the authors identify which aspects of realism most improve transfer to real documents. Using these insights, they adapt a large PaddleOCR model into Wayu‑Paxa‑OCR‑Zero, achieving a median character error rate of 1.24% on printed pages and 20.55% on handwriting, outperforming existing Thai OCR systems.
arXiv Computation and Language
Sep 4
Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards
Jina-OCR-v1 is an end‑to‑end document parsing model designed for low‑budget GPUs, combining a compressed‑vision encoder with a 3B mixture‑of‑experts decoder that activates about 570 M parameters per token. It uses a FastMTP speculative decoding head that shares a single draft block across three prediction steps, with greedy verification ensuring lossless decoding. Post‑training includes instruction alignment, robustness fine‑tuning on difficult documents, and GRPO with dense verifiable rewards, achieving 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR‑Bench while delivering the highest page throughput at 2.57 pages per second on an NVIDIA L4 GPU.
arXiv Computer Vision
Oct 5
HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers
HakushoBench is a Japanese chart and table visual question answering benchmark created from 33 governmental white papers, comprising 2,053 images across more than ten types. The dataset includes manually annotated and independently verified QA pairs that evaluate holistic understanding of charts and tables rather than just local visual cues. Experiments show that HakushoBench is significantly harder than existing Japanese benchmarks, with sub‑10B open‑weight models achieving at most 58.6% accuracy and even large models like Qwen3.5-397B-A17B lagging behind Gemini‑3‑Pro by 8.1 points.
arXiv AI
Aug 11
TongGuOCR: A Layout-Aware and Token-Augmented OCR Framework for Chinese Historical Documents
arXiv:2608. 07917v1 Announce Type: new Abstract: Chinese historical documents preserve valuable cultural heritage, but many collections remain accessible only as scanned page images, preventing full-text retrieval, collation, and computational analysis.
arXiv Computation and Language
1d ago
Unlimited OCR Works 2
Unlimited OCR 2 is a document parsing model that processes only the text it transcribes, avoiding re‑scanning earlier pages. It replaces all decoder attention with Sparse Reference Sliding Window Attention (SR‑SWA), keeping computational costs constant regardless of document length. The model achieves significant per‑step speedups over Full Attention and R‑SWA, and sets new state‑of‑the‑art results on the MPDocBench and MarathonDocBench benchmarks for hundred‑page documents.
arXiv Machine Learning
Aug 13
Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models
arXiv:2605. 16409v3 Announce Type: replace-cross Abstract: Optical character recognition (OCR) and multilingual scene-text understanding remain challenging for multimodal large language models (MLLMs), particularly in real-world images containing small or degraded text, cluttered layouts, occlusion, handwriting, and complex typography.