mlsanityData to 7 Oct 2026

GLM-OCR Technical Report

arXiv 2603.10910 ↗First posted 11 Mar 2026cs.CLcited by 24

Not on the map. Why?

Abstract (arXiv)

GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM language decoder, achieving a strong balance between computational efficiency and recognition performance. To address the inefficiency of standard autoregressive decoding in deterministic OCR tasks, GLM-OCR introduces a Multi-Token Prediction (MTP) mechanism that predicts multiple tokens per step, significantly improving decoding throughput while keeping memory overhead low through shared parameters. At the system level, a two-stage pipeline is adopted: PP-DocLayout-V3 first performs layout analysis, followed by parallel region-level recognition. Extensive evaluations on public benchmarks and industrial scenarios show that GLM-OCR achieves competitive or state-of-the-art performance in document parsing, text and formula transcription, table structure recovery, and key information extraction. Its compact architecture and structured generation make it suitable for both resource-constrained edge deployment and large-scale production systems.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 21 of its 28 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

21 of 28 references.

References · 21

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  4. 2025Qwen2.5-VL Technical Reportcited by 5,418
  5. 2025Qwen3-VL Technical Reportcited by 2,534
  6. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  7. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  8. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  9. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 502
  10. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
  11. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 439
  12. 2025Seed1.5-VL Technical Reportcited by 367
9 more
  1. 2019Image-based table recognition: data, model, and evaluationcited by 233
  2. 2025DeepSeek-OCR: Contexts Optical Compressioncited by 174
  3. 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Modelscited by 120
  4. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 108
  5. 2025PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Modelcited by 84
  6. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 81
  7. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 78
  8. 2026PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsingcited by 54
  9. 2025POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversioncited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 24.

24 papers.

Sort:

By area:

  1. 2026MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scalecited by 26
  2. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  3. 2026OvisOCR2 Technical Reportcited by 5
  4. 2026MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarioscited by 4
  5. 2026RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inferencecited by 4
  6. 2026Infinity-Parser2 Technical Reportcited by 4
  7. 2026MonkeyOCRv2: A Visual-Text Foundation Model for Document AIcited by 4
  8. 2026ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correctioncited by 2
  9. 2026The Character Error Vector: Decomposable errors for page-level OCR evaluationcited by 1
  10. 2026MinerU-Popo: Universal Post-Processing Model for Structured Document Parsingcited by 1
  11. 2026FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarkscited by 1
  12. 2026All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Expertscited by 1
12 more
  1. 2026MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsingcited by 0
  2. 2026HPD-Parsing: Hierarchical Parallel Document Parsingcited by 0
  3. 2026When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoningcited by 0
  4. 2026Mapping Armenian Paris: Extracting and Geocoding Commercial Advertisements from the 20th-Century Diaspora Presscited by 0
  5. 2026WildHandBench: A Benchmark for Handwritten Text Understanding that Challenges MLLMs and Humanscited by 0
  6. 2026MoTE: Mixture of Task Experts for Multi-Task Video Understandingcited by 0
  7. 2026Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewardscited by 0
  8. 2026From Retrieval to Recognition:How Vision--Language Models Become OCR Specialistscited by 0
  9. 2026Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsingcited by 0
  10. 2026DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documentscited by 0
  11. 2026Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decodingcited by 0
  12. 2026Xiaomi-OCR-0 Technical Reportcited by 0