TeleOCR is a roughly 1.2-billion-parameter vision-language model designed to turn digital documents and camera-captured pages—including geometrically distorted pages—into structured output such as text, tables, formulas, and page layouts. Its authors combine deformation-aware training with separate learning for table and formula structure. The project reports strong benchmark scores, but those figures are self-reported and should not be treated as independent validation.
What TeleOCR does
Document parsing goes beyond recognizing characters: it aims to transform a page into machine-readable content while preserving relationships such as reading order, table rows and columns, and mathematical notation. TeleOCR targets both clean digital documents and photographed pages, including pages affected by geometric distortion. The paper frames this as a way to handle varied input in one system rather than relying on a separate dewarping model for photographed pages.
The project model card lists task modes for text, tables, formulas, code, layout, polygon-based layout for distorted pages, and converting scientific charts into tables. The task is selected through a prompt. For complete document parsing, the model card points users to the project’s parsing repository: TeleOCR parsing repository. [c004]
How the model is designed to handle document structure
The paper identifies two broad challenges. In a pipeline that separates layout analysis from recognition, an early layout error can affect later text recognition. End-to-end vision-language systems, in turn, can generate redundant or hallucinated content and may struggle with structural reasoning at high resolution. TeleOCR proposes methods intended to address these issues; the paper’s description is not, by itself, proof that each method improves results in every deployment.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
Four-stage training
The TeleOCR materials describe training in four stages:
- Pretraining for document parsing.
- Deformation-aware training for pages whose geometry is distorted.
- Separate learning of table and formula structure from their content.
- Reinforcement learning using task-specific rewards.
Representing curved or distorted pages
For distorted pages, the described method uses polygon outlines to represent layout regions and a grid of control points to represent page deformation. The project also describes Curvature-Guided Douglas–Peucker Sampling to place polygon vertices and Multi-node Consensus Voting to generate pseudo-labels from multiple parsers. These are components of the authors’ proposed method, not independently established measures of deployment quality.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
Architecture and output formats
An NYU Shanghai RITS explainer describes the model as using a Qwen2.5-VL vision encoder, a Qwen3-0.6B language model, and an MLP aligner trained from scratch. That is the explainer’s account of the design, based on project materials. The project describes outputs including ordinary text, tables in OTSL-style markup, LaTeX formulas, code blocks, page layouts, polygon layouts for distorted pages, and tables inferred from scientific charts. It also describes a layout-first, recognition-second workflow that does not require a separate rectification model. [c003]
What the reported benchmark results show—and do not show
The scores below are reported by the TeleOCR project in its model card and discussed by the NYU Shanghai RITS explainer. They are not independent test results. Comparisons are meaningful only when the benchmark version, evaluation setup, metric direction, and comparison cohort match. [c002] [c003]
Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Clear out junk files and repair common Windows errors3Fix the driver behind crashes, sound loss and screen glitchesRank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
| Benchmark or challenge | Project-reported result | How to interpret it |
|---|---|---|
| OmniDocBench v1.6 | 96.87 overall; TeleOCR model card, 2026 | The model card lists additional submetrics, including text edit 0.027, formula CDM 96.36, table TEDS 97.05, table TEDS-S 98.52, and read-order edit 0.122. Metric directions differ, so a larger number is not always better. The RITS explainer notes that the project table does not lead on every submetric: it reports a lower text-edit value for OvisOCR2 and a higher formula CDM for OvisOCR2. [c002] [c003] |
| Wild_OmniDocBench | 88.53 overall; TeleOCR project, 2026 | A project-reported result; comparisons depend on the cohort and evaluation setup shown with the score. [c002] |
| PureDocBench | 78.41 overall; TeleOCR project, 2026 | The RITS explainer describes this as an average across clean, digitally degraded, and real-degraded pages. For the real-degraded subset alone, it reports 70.85 for TeleOCR and 71.98 for Gemini-3.1-Pro. [c003] |
| ICDAR 2026 Sci-ImageMiner Challenge | 41.81 weighted score and first place; TeleOCR project, 2026, as relayed by the RITS explainer | The placement and score are reported by the project and relayed by the explainer. [c003] |
| EMNLP 2026 Dr.DocBench Challenge | 67.96; TeleOCR model card, 2026 | The model card presents this as a self-run comparison using native weights. The RITS explainer cautions that it is not a leaderboard placement. [c002] [c003] |
These results suggest that the project evaluates more than plain text recognition, including layout, tables, formulas, and degraded-page cases. They do not establish a universal ranking. A useful comparison should match benchmark version and evaluation setup, then examine text error, formula recognition, table structure, reading order, performance on photographed or degraded pages, model size, and deployment requirements. An overall score can obscure trade-offs between those tasks.
Benchmark caveats to keep in mind
The RITS explainer says the release’s comparisons are the authors’ own and recommends checking competitor figures against benchmark repositories. It also flags apparently duplicated submetrics for HunyuanOCR-1.5 and PaddleOCR-VL-1.6 in the project table as a likely transcription error. Treat the published tables as project-reported evidence, not as an independently audited leaderboard. [c003]
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
The paper proposes a unified approach and the project reports evaluation results, but the materials described here do not establish independent replication, production throughput, or a validated minimum GPU configuration. The model card’s inference examples show usage patterns; they are not a hardware qualification study. [c001] [c002]
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Access, naming, and licensing
The model card says weights and a technical report were released under the name NaviDC-OCR on August 17, 2026, and that the project was renamed TeleOCR on September 10, 2026. The card includes local inference-server examples and records a community GGUF conversion for llama.cpp. It also stated, when accessed, that the model was not deployed by an Inference Provider on that page. These details can change, so check the current model card and repository for the version and inference options you intend to use. [c002] [c004]
Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
An NYU Shanghai RITS article dated September 29, 2026, reports that the release uses Apache 2.0. Check the current repository’s license materials for the weights, code, and dependencies before deciding whether a particular use is covered. [c003]
Who should consider TeleOCR?
TeleOCR is relevant if you need structured extraction from a mix of digital documents and photographed or distorted pages, especially when tables, formulas, layout, or reading order matter alongside text. Its prompt-selected task modes and local inference examples may also interest teams evaluating an open model for document workflows. The reported benchmark scores are a reason to test it, not a substitute for testing it against your own documents and evaluation criteria.
Quick Recap
- Compare outputs on representative pages, including the distortions, languages, table types, and formula styles you actually encounter.
- Inspect structural correctness as well as recognized text: a plausible transcription can still have incorrect table relationships or reading order.
- Verify the current weights, repository, license terms, and inference setup before integrating the model.
- Do not assume a specific GPU, throughput, or production result from the example snippets; the cited materials do not establish those requirements.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
