OCR papers, 2023–2026
Optical character recognition
Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 14 papers are tagged with this topic.
Key findings
- OCR went from 1 papers in 2023 to 5 in 2026, roughly 5.0x in three years.
- CVPR publishes the most OCR work: 7 papers from 2023 to 2026, 50% of the four-venue total.
- Among the 5 topics under Document and Layout, it ranks #4 by 2026 paper count; the fastest grower in the group, PDF Understanding, is up 6.5x versus 5.0x here.
Papers per venue
Counts by year and venue
| Year | NeurIPS | ICLR | ICML | CVPR | Total |
|---|---|---|---|---|---|
| 2023 | 0 | 0 | 0 | 1 | 1 |
| 2024 | 2 | 0 | 1 | 2 | 5 |
| 2025 | 2 | 0 | 0 | 1 | 3 |
| 2026 | 0 | 1 | 1 | 3 | 5 |
Representative papers
Spread across years and venues so every edition shows up
- ICML 2026Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR
- ICLR 2026Teaching VLMs to Admit Uncertainty in OCR from Lossy Visual Inputs
- CVPR 2026PIX-TAB Efficient PIXel-Precise TABle Structure Recognition Approach with Speculative Decoding
- NeurIPS 2025MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
- CVPR 2025CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR
- NeurIPS 2024Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition
- ICML 2024UPOCR: Towards Unified Pixel-Level OCR Interface
- CVPR 2024Atom-Level Optical Chemical Structure Recognition with Limited Supervision
- CVPR 2023Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
- CVPR 2026Consensus Entropy Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
- NeurIPS 2025Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
- NeurIPS 2024General Detection-based Text Line Recognition
- CVPR 2024Dense Optical Tracking: Connecting the Dots
- CVPR 2026Optical Flow Matching Reframing Optical Flow as Continuous Transport Dynamics
All OCR papers
4 papers, page 1 of 1
- NeurIPS 2025MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
- NeurIPS 2025Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
- NeurIPS 2024General Detection-based Text Line Recognition
- NeurIPS 2024Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition
Ask about this trend from Claude or Cursor
Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.
Copy this prompt into your assistant
Use paperlist to show how OCR papers grew at CVPR from 2023 to 2026, and which year jumped the most.
Tool the assistant calls: get_topic_stats {"topic": "ocr"}
Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)
FAQ
- How many OCR papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?
- 14 in total: 1 in 2023, 5 in 2024, 3 in 2025, 5 in 2026.
- How many OCR papers are at NeurIPS 2025?
- NeurIPS 2025 has 2 OCR papers, versus 2 the year before.
- How many OCR papers are at ICLR 2026?
- ICLR 2026 has 1 OCR papers.
- How many OCR papers are at ICML 2026?
- ICML 2026 has 1 OCR papers.
- How many OCR papers are at CVPR 2026?
- CVPR 2026 has 3 OCR papers, versus 1 the year before.
- Which conference publishes the most OCR papers?
- CVPR, with 7 papers from 2023 to 2026.