REVIEW 15 cited by
Ocean-OCR: Towards General OCR Application via a Vision-Language Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Ocean-OCR: Towards General OCR Application via a Vision-Language Model
read the original abstract
Multimodal large language models (MLLMs) have shown impressive capabilities across various domains, excelling in processing and understanding information from multiple modalities. Despite the rapid progress made previously, insufficient OCR ability hinders MLLMs from excelling in text-related tasks. In this paper, we present \textbf{Ocean-OCR}, a 3B MLLM with state-of-the-art performance on various OCR scenarios and comparable understanding ability on general tasks. We employ Native Resolution ViT to enable variable resolution input and utilize a substantial collection of high-quality OCR datasets to enhance the model performance. We demonstrate the superiority of Ocean-OCR through comprehensive experiments on open-source OCR benchmarks and across various OCR scenarios. These scenarios encompass document understanding, scene text recognition, and handwritten recognition, highlighting the robust OCR capabilities of Ocean-OCR. Note that Ocean-OCR is the first MLLM to outperform professional OCR models such as TextIn and PaddleOCR.
Forward citations
Cited by 15 Pith papers
-
Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models
General-purpose VLMs systematically rewrite perturbed words back to the original — up to 4.5 WER points on English — with rewriting tied to representation similarity and word length.
-
Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks
Multimodal ICL lags text-only ICL in few-shot settings due to weak cross-modal reasoning alignment and unreliable task mapping transfer, with an inference-stage method proposed to strengthen transfer.
-
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
A fixed 1.2B model trained via diversity-aware sampling, cross-model verification, annotation refinement, and progressive stages achieves new state-of-the-art document parsing accuracy of 95.69 on OmniDocBench v1.6.
-
From Plausibility to Verifiability: Risk-Controlled Generative OCR with Vision-Language Models
A model-agnostic Geometric Risk Controller reduces extreme errors in VLM-based OCR by requiring cross-view consensus before accepting outputs.
-
HPD-Parsing: Hierarchical Parallel Document Parsing
Hierarchical parallel decoding — a global layout branch plus concurrent content branches with multi-token prediction — reaches 4,752 tokens/sec (≈3× a vanilla autoregressive baseline) at competitive accuracy on OmniDocBench.
-
DocAtlas: Multilingual Document Understanding Across 80+ Languages
DocAtlas introduces model-free rendering pipelines to create DocTag-annotated datasets across 82 languages and shows DPO adaptation improves multilingual performance without base-language degradation.
-
DocAtlas: Multilingual Document Understanding Across 80+ Languages
DocAtlas creates multilingual document datasets across 82 languages and shows DPO with rendered ground truth improves model accuracy by 1.7-1.9% without degrading base-language performance, unlike supervised fine-tuning.
-
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference
RTPrune prunes visual tokens in DeepSeek-OCR via a reading-twice two-stage process, retaining 84.25% tokens for 99.47% accuracy and 1.23x faster prefill on OmniDocBench.
-
Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild
A full-scale physical reconstruction of OmniDocBench with five distortion scenarios shows all document-parsing models degrade in the real world, with the authors' PaddleOCR-VL-1.5 topping the leaderboard.
-
HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding
A training-free, two-stage speculative decoding scheme accelerates VLM document parsers by ~2.8x end-to-end (up to 7x) while keeping parsing accuracy essentially unchanged.
-
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
MinerU2.5 uses a two-stage decoupled vision-language architecture to achieve state-of-the-art document parsing accuracy with lower computational overhead than existing general and domain-specific models.
-
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference
RTPrune introduces a reading-twice inspired two-stage pruning technique for DeepSeek-OCR that retains 84.25% tokens while delivering 99.47% accuracy and 1.23x faster prefill on OmniDocBench.
-
UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters
A 0.1B-parameter text/formula recognition model trained on a new 40M-sample dataset matches or beats much larger OCR models and runs 2-9× faster.
-
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference
RTPrune delivers 99.47% accuracy and 1.23x faster prefill on OmniDocBench for DeepSeek-OCR-Large by retaining only 84.25% of tokens through a reading-twice inspired two-stage pruning process.
-
Evaluating Vision-Language Models as a Zero-Shot Learning Alternative to You Only Look Once and Optical Character Recognition for Nigerian License Plate Recognition
Five VLMs are benchmarked on 88 Nigerian license plate images; Gemini and Qwen achieve lower character error rates than GPT-4o, Claude, and Llama in a zero-shot setting.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.