Update README.md

README.md

@@ -16,21 +16,21 @@ tags:
 <div align="center">
 
 <h1 align="center">
-NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
+TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
 
 </h1>
 
 [![License](https://img.shields.io/badge/License-Apache--2.0-blue.svg)](LICENSE)
-[![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/caipeng328/NaviDC-OCR)
+[![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/caipeng328/TeleOCR)
 [![Papers with Code: SOTA on OmniDocBench v1.6](https://paperswithcode.co/api/v1/papers/2608.12898/leaderboard-badge.svg?eval=25856&live=1)](https://paperswithcode.co/api/v1/papers/2608.12898/leaderboard-badge-link?eval=25856)
 </div>
 
 <div align="center">
-  <img src="https://raw.githubusercontent.com/caipeng328/NaviDC-OCR/refs/heads/main/assets/score.png" width="800">
+  <img src="https://raw.githubusercontent.com/caipeng328/TeleOCR/refs/heads/main/assets/score.png" width="800">
 </div>
 
 ## 🔥 News
-
+- **2026/09/10** - We have renamed NaviDC-OCR to TeleOCR, and all subsequent model iterations will be developed and released under the TeleOCR version.
 - **2026/09/01** - We noticed that EMNLP 2026 is hosting the [Dr.DocBench Challenge](https://eval.ai/web/challenges/challenge-page/2717/overview), a document parsing competition. We evaluated NaviDC-OCR with its native weights, achieving better results than MinerU 2.5 Pro and PaddleOCR-VL 1.6. Detailed results are shown below **dr.docbench-challenge**. We welcome the use of NaviDC‑OCR for competitions. Going forward, we will continue to deliver competitive parsing models for the community.
 - **2026/08/29** — Thanks to Nandraj for the GGUF conversion and llama.cpp support!  [🔗 NaviDC-OCR-GGUF](https://huggingface.co/nandraj/NaviDC-OCR-GGUF)
 - **2026/08/17** — NaviDC-OCR [model weights](https://huggingface.co/StarDoc-AI/NaviDC-OCR) and [technical report](https://arxiv.org/pdf/2608.12898) have been released.
@@ -38,11 +38,11 @@ NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Docum
 
 ## 📖 Introduction
 
-**NaviDC-OCR** is a lightweight (~1.2B parameters), open-source Vision-Language Model designed specifically for document parsing.
+**TeleOCR** is a lightweight (~1.2B parameters), open-source Vision-Language Model designed specifically for document parsing.
 
-Unlike existing methods that mainly target either digital documents or camera-captured documents, NaviDC-OCR unifies both scenarios within a single framework.
+Unlike existing methods that mainly target either digital documents or camera-captured documents, TeleOCR unifies both scenarios within a single framework.
 
-Compared with previous document parsing models, NaviDC-OCR introduces
+Compared with previous document parsing models, TeleOCR introduces
 
 - Multi-node Consensus Voting (MCV) for automatic pseudo-label generation
 - Geometry-aware document modeling for camera-captured documents
@@ -51,18 +51,18 @@ Compared with previous document parsing models, NaviDC-OCR introduces
 - Progressive four-stage training pipeline
 - Content-Structure Decoupled Learning for tables and formulas
 
-These techniques enable NaviDC-OCR to achieve state-of-the-art performance on both digital and camera-captured document benchmarks while remaining lightweight enough for practical deployment.
+These techniques enable TeleOCR to achieve state-of-the-art performance on both digital and camera-captured document benchmarks while remaining lightweight enough for practical deployment.
 
 ## 📊 Experimental Results
 
-NaviDC-OCR  achieves state-of-the-art performance on multiple public document parsing benchmarks.
+TeleOCR  achieves state-of-the-art performance on multiple public document parsing benchmarks.
 
 ### Layout Visualization of Distorted Documents
-To evaluate the model's ability to understand complex document deformations, we conduct a visual evaluation on the public dewarping datasets DocUNet and DIR300, with representative results shown in Figure. NaviDC-OCR directly performs layout and content parsing on distorted documents without dewarping preprocessing or a dedicated rectification model, demonstrating robust parsing under complex geometric deformations.
+To evaluate the model's ability to understand complex document deformations, we conduct a visual evaluation on the public dewarping datasets DocUNet and DIR300, with representative results shown in Figure. TeleOCR directly performs layout and content parsing on distorted documents without dewarping preprocessing or a dedicated rectification model, demonstrating robust parsing under complex geometric deformations.
 <div align="center">
 
-<img src="https://raw.githubusercontent.com/caipeng328/NaviDC-OCR/refs/heads/main/assets/dir300.png" width="800" alt="Parsing evaluation on the DIR300 dataset.">
-<img src="https://raw.githubusercontent.com/caipeng328/NaviDC-OCR/refs/heads/main/assets/docunet.png" width="800" alt="Parsing evaluation on the DocUNet dataset.">
+<img src="https://raw.githubusercontent.com/caipeng328/TeleOCR/refs/heads/main/assets/dir300.png" width="800" alt="Parsing evaluation on the DIR300 dataset.">
+<img src="https://raw.githubusercontent.com/caipeng328/TeleOCR/refs/heads/main/assets/docunet.png" width="800" alt="Parsing evaluation on the DocUNet dataset.">
 </div>
 
 ---
@@ -72,7 +72,7 @@ To evaluate the model's ability to understand complex document deformations, we
 |模型|overall ↑|Text edit ↓|formula cdm ↑|Table teds ↑|order edit ↓|
 |---|---|---|---|---|---|
 |**Specialized VLMs**| | | | | |
-|Navidc‑OCR|67.96|0.1903|0.02|64.97|0.398|
+|TeleOCR|67.96|0.1903|0.02|64.97|0.398|
 |Mineru 2.5 pro|62.26|0.3402|0.04|67.75|0.356|
 |OvisOCR2|59.25|0.3883|0.00|61.59|0.3791|
 |PaddleOCRvl 1.6|55.11 | 0.4364 | 0.21 | 51.34 |0.412 |
@@ -84,7 +84,7 @@ To evaluate the model's ability to understand complex document deformations, we
 
 | Model Type | Methods | Param | Overall ↑ | Text Edit ↓ | Formula CDM ↑ | Table TEDS ↑ | Table TEDS-S ↑ | Read Order Edit ↓ |
 |---|---|---:|---:|---:|---:|---:|---:|---:|
-| **Specialized VLMs** | **NaviDC-OCR** | **1.2B** | **96.87** | <u>0.027</u> | 96.36 | **97.05** | **98.52** | <u>0.122</u> |
+| **Specialized VLMs** | **TeleOCR** | **1.2B** | **96.87** | <u>0.027</u> | 96.36 | **97.05** | **98.52** | <u>0.122</u> |
 | | OvisOCR2 | 0.8B | <u>96.58</u> |  **0.025** | **97.53** | <u>94.76</u> | <u>97.16</u> | **0.111** |
 | | PaddleOCR-VL-1.6 | 0.9B | 96.33 | 0.033 | <u>97.49</u> | <u>94.76</u> | 97.11 | 0.127 |
 | | MinerU2.5-Pro | 1.2B | 95.75 | 0.036 | 97.45 | 93.42 | 95.92 | 0.120 |
@@ -116,7 +116,7 @@ To evaluate the model's ability to understand complex document deformations, we
 ### [Wild_OmniDocBench](https://github.com/VirtualLUOUCAS/Wild_OmniDocBench) 
 | Model Type          | Methods           | Param |    Overall ↑ | Text Edit ↓ | Formula CDM ↑ | Table TEDS ↑ | Table TEDS-S ↑ | Read Order Edit ↓ |
 | ------------------- | ----------------- | ----: | -----------: | ----------: | ------------: | -----------: | -------------: | ----------------: |
-| **Decoupled VLMs**  | **NaviDC-OCR**    |  1.2B |    **88.53** |  **0.1173** |         88.26 |    **89.05** |      **92.14** |        **0.2011** |
+| **Decoupled VLMs**  | **TeleOCR**    |  1.2B |    **88.53** |  **0.1173** |         88.26 |    **89.05** |      **92.14** |        **0.2011** |
 |                     | PaddleOCR-VL-1.6  |  0.9B |        87.36 |      0.1369 |         88.42 | <u>85.76</u> |   <u>90.14</u> |            0.2057 |
 |                     | MinerU2.5-Pro     |  1.2B |        87.33 |      0.1362 |  <u>90.15</u> |        85.46 |          90.12 |     <u>0.2013</u> |
 |                     | GLM-OCR           |  0.9B |        85.08 |      0.1514 |         89.09 |        81.31 |          85.90 |            0.2228 |
@@ -132,7 +132,7 @@ To evaluate the model's ability to understand complex document deformations, we
 ### [PureDocBench](https://github.com/zhihengli-casia/puredocbench/)
 | Model Type         | Model             | Clean Overall ↑ | Clean Text ↓ | Clean Formula ↑ | Clean Table ↑ | Digital Degraded Overall ↑ | Digital Degraded Text ↓ | Digital Degraded Formula ↑ | Digital Degraded Table ↑ | Real Degraded Overall ↑ | Real Degraded Text ↓ | Real Degraded Formula ↑ | Real Degraded Table ↑ |
 | ------------------ | ----------------- | --------------: | -----------: | --------------: | ------------: | -------------------------: | ----------------------: | -------------------------: | -----------------------: | ----------------------: | -------------------: | ----------------------: | --------------------: |
-| **Decoupled VLM**  | **NaviDC-OCR**    |       **86.90** |    **0.111** |       **81.01** |     **91.09** |               <u>77.47</u> |                   0.206 |                  **72.59** |                    80.45 |               **70.85** |         <u>0.302</u> |               **65.11** |             **77.66** |
+| **Decoupled VLM**  | **TeleOCR**    |       **86.90** |    **0.111** |       **81.01** |     **91.09** |               <u>77.47</u> |                   0.206 |                  **72.59** |                    80.45 |               **70.85** |         <u>0.302</u> |               **65.11** |             **77.66** |
 |                    | DotsMOCR          |           76.27 |        0.151 |           66.23 |         77.65 |                      73.16 |            <u>0.198</u> |                      64.32 |                    74.95 |                   61.73 |                0.312 |                   54.39 |                 61.97 |
 |                    | MinerU2.5-Pro     |           75.87 |        0.222 |           65.14 |         84.68 |                      71.77 |                   0.272 |                      61.79 |                    80.73 |                   62.56 |                0.375 |                   52.70 |                 72.47 |
 |                    | YouTu-Parsing     |           75.02 |        0.230 |           67.34 |         80.74 |                      69.66 |                   0.270 |                      61.44 |                    74.49 |                   60.29 |                0.360 |                   52.20 |                 64.69 |
@@ -156,7 +156,7 @@ To evaluate the model's ability to understand complex document deformations, we
 ### [ICDAR2026 Sci-ImageMiner](https://sites.google.com/view/sci-imageminer/)
 |     # | Team            |       RMS |      TEDS |  Weighted |
 | ----: | --------------- | --------: | --------: | --------: |
-| **1** | **NaviDC-OCR**  | **17.23** | **66.39** | **41.81** |
+| **1** | **TeleOCR**  | **17.23** | **66.39** | **41.81** |
 |     2 | VLMinators      |     17.29 |     64.31 |     40.80 |
 |     3 | Ricoh_SRCB      |     16.23 |     61.12 |     38.67 |
 |     4 | Vassilis Sioros |     14.94 |     55.20 |     35.07 |
@@ -353,9 +353,9 @@ def infer(image: Image.Image, prompt: str) -> str:
 
 
 
-processor = AutoProcessor.from_pretrained("StarDoc-AI/NaviDC-OCR", trust_remote_code=True, use_fast=True)
+processor = AutoProcessor.from_pretrained("StarDoc-AI/TeleOCR", trust_remote_code=True, use_fast=True)
 model = AutoModel.from_pretrained(
-    "StarDoc-AI/NaviDC-OCR",
+    "StarDoc-AI/TeleOCR",
     trust_remote_code=True,
     torch_dtype=torch.bfloat16,
 ).cuda().eval()
@@ -405,8 +405,8 @@ If you would like to perform complete document parsing, please refer to our GitH
 ## Citation
 
 ```bibtex
-@article{navidc_ocr,
-  title={NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents},
+@article{teleocr,
+  title={TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents},
   author={Cai, Peng and Zou, Zhaofan and Liu, Shifa and Wang, Yikun and Tang, Jiawei and Yang, Kaicheng and Tong, Meng and He, Zhongjiang and Sun, Hao},
   journal={arXiv preprint arXiv:2608.12898},
   year={2026}
@@ -418,7 +418,7 @@ Thanks to Nandraj for the GGUF conversion and llama.cpp support!  [🔗 NaviDC-O
 
 ## Acknowledgements
 
-NaviDC-OCR is built upon
+TeleOCR is built upon
 
 - MinerU
 - Qwen2.5-VL