Voxel51

• Explore, tinker with, and push the boundaries of the latest AI and machine learning technologies to showcase what's possible with open-source tools and frameworks

• Build inspiring prototypes, proof-of-concepts, and example applications that demonstrate creative and impactful uses of AI to the developer community

• Contribute meaningfully to the open source ecosystem by creating and maintaining libraries, tools, datasets, tutorials and guides that enable developers to more easily leverage AI capabilities

• Curate, clean, annotate and publish unique multimodal datasets spanning text, images, audio, video, 3D and other emerging data types to facilitate novel machine learning research and applications

• Create engaging technical blog posts, social media content, videos, and presentations that educate and inspire developers and data scientists to build with AI

•  Collaborate openly with our internal teams and the broader AI/ML community to cross-pollinate ideas, share knowledge, and collectively advance the state-of-the-art

• Evangelize our technology and vision by representing the company at hackathons, conferences, meetups, universities, and other developer-focused events

•  Influence the product roadmap by providing input on the developer experience, uncovering opportunities for new features and improvements based on community feedback and your work

• Continuously learn, experiment with, and provide feedback on beta versions of our latest models and capabilities to help shape the future of our platform

Hacker-in-Residence

LinkedIn

1) Introductory computer vision course for LinkedIn Learning

2) Prompt Engineering with LangChain (releasing March 2024)

3) RetrievalAugemnted Generation with LlamaIndex (releasing Q2 2024)

4) Fine-tuning LLMs with Hugging Face TRL (est release Q3 2024)

5) Text Generation with Hugging Face Transformers (est release Q3 2024)

LinkedIn Learning Instructor

The Artists of Data Science

The ONLY personal growth and development podcast for Data Scientists

Host

Deci AI

Developer Relations Manager

Pachyderm Inc.

Senior Developer Advocate

Comet

ML Developer Advocate

Data Science Dream Job

Principal Data Science Educator

Price Industries

Lead Data Scientist

Bold Commerce

Senior Data Scientist

Emergent BioSolutions

Biostatistician

I create content about deep learning | The DevRel and Deep Learning Dude

Hacking on LLMs, curating multimodal datasets, and writing a book about RAG.

Harpreet Sahota 🥑

sam3 is seriously a step change improvement over sam2

the model is seriously good, glad they brought back text prompts. the automatic segmentation isn't as good as i hoped it to be...but it still works quite well. 

i also got it to output image embeddings and that was cool to visualize in the app

learn more here: https://lnkd.in/gzqJzj6G

🤖 Hacker-in-Residence @ Voxel51| 👨🏽‍💻 AI/ML Engineer | 👷🏽‍♀️ Technical Developer Advocate | Learn. Do. Write. Teach. Repeat.

qwen3vl is literally the best model i've used for video usecases. blows my mind

hosting a virtual event tomorrow about document ai

you may or may not find it interesting, but i guarantee you'll learn something

join me here: https://lnkd.in/dFXPimVc

sony ai released a pretty cool dataset called the fairness human centric image benchmark, super high quality labels

instructions for downloading and parsing the dataset into fiftyone format can be found here: https://lnkd.in/g_VwxJx4

physical AI is top of mind as the next frontier for deep learning. but it'll only succeed if you have good datasets

language models scaled with web-scale text. 

vision models got ImageNet. 

now Voxel51 and NVIDIA are trying to do the same thing for physical AI 

autonomous vehicles, humanoid robots, anything that moves around atoms.

building these systems means millions of hours of testing in high-fidelity sims before you can actually deploy anything. 

petabytes of multimodal sensor data from various modalities

 LiDAR, cameras, radar, IMUs. 

but over 50% of simulations end up completely unusable because the input data is bad.

even small calibration or timing errors between sensors cascade through your neural reconstructions. 

you waste weeks and burn through millions in compute costs before you realize what went wrong.

the new FiftyOne Physical AI Workbench. it integrates with NVIDIA Omniverse and NVIDIA Cosmos and basically sits at the start of your sim pipeline to validate, clean up, and prep your multimodal data before it hits neural reconstruction and synthetic data generation.

what it does:

- automatically audits physical AI inputs across 75+ critical checkpoints

- transforms raw sensor streams into structured, searchable datasets

- triggers accurate neural reconstructions and generates synthetic scene variations

this means fewer wasted compute hours. 

iteration loops go from weeks to hours. 

you build safer, more reliable systems on data you can actually trust.

read more about what we've been building: https://lnkd.in/gC6_zn-X

i recently integrated 4 ocr models into fiftyone as remote zoo models these handle text extraction and document parsing. 

all available as remote zoo sources, you can get started with a few lines of code

different approaches for different needs:

1. mineru-2.5

1.2b params, two-stage strategy: global layout on downsampled image, then fine-grained recognition on native-resolution crops. 

handles headers, footers, lists, code blocks. strong on complex math formulas (mixed chinese-english) and tables (rotated, borderless, partial-border).

good for: documents with complex layouts and mathematical content

https://lnkd.in/dSwimdvp

deepseek-ocr

dual-encoder (sam + clip) for "contextual optical compression." 

outputs structured markdown with bounding boxes. has five resolution modes (tiny/small/base/large/gundam). gundam mode is the default - uses multi-view processing (1024×1024 global + 640×640 patches for details). 

supports custom prompts for specific extraction tasks.

good for: complex pdfs and multi-column layouts where you need structured output

https://lnkd.in/dhJn2h-v

olmocr-2

built on qwen2.5-vl, 7b params. outputs markdown with yaml front matter containing metadata (language, rotation, table/diagram detection). 

converts equations to latex, tables to html. labels figures with markdown syntax. reads documents like a human would.

good for: academic papers and technical documents with equations and structured data

https://lnkd.in/dNdTQYKg

kosmos-2.5

microsoft's 1.37b param multimodal model. two modes: ocr (text with bounding boxes) or markdown generation. automatically optimizes hardware usage (bfloat16 for ampere+, float16 for older gpus, float32 for cpu). handles diverse document types including handwritten text.

good for: general-purpose ocr when you need either coordinates or clean markdown

https://lnkd.in/dCTfGfV8


two modes typical across these models: detection (bounding boxes) and extraction (text output)

i also built/revamped the caption viewer plugin for better text visualization in the app: 

https://lnkd.in/dBebWdga

i've also got two events poppin off for document visual ai:

- nov 6 (tomorrow) with a stellar line up of speakers: https://lnkd.in/gkBEY4_r

- a deep dive into document visual ai with just me: 

https://lnkd.in/dFXPimVc

Open article: Document Visual AI with FiftyOne - November 14, 2025 by voxel51.com

Document Visual AI with FiftyOne - November 14, 2025

hype for this new integration, and proud of the team for shipping it at lightning speed. big ups to Daniel and AdonAI for goin beast mode on this one

🚀 Introducing Physical AI Workbench — integrated with NVIDIA Omniverse NuRec and NVIDIA Cosmos to solve the biggest bottleneck in physical AI.  

More than half of all physical AI simulations fail — not from bad models, but from bad input data. A timestamp off by milliseconds or a calibration drift of a few degrees can cascade through your neural reconstructions, leaving you with unusable results after weeks and millions in wasted compute. 

FiftyOne Physical AI Workbench sits at the start of your simulation pipeline and provides turnkey access to NVIDIA technology to ensure every simulation run begins with trustworthy data: 

✅ Audits 75+ critical checkpoints to ensure every reconstruction starts with validated inputs 
🎯 Enriches raw sensor streams into structured, searchable datasets 
🔗 Integrates directly with NVIDIA Omniverse and NVIDIA Cosmos for high-fidelity reconstruction and synthetic data generation. 

The result: an end-to-end workflow that prevents downstream failures — cutting iteration cycles from weeks to hours and eliminating GPU waste on failed reconstructions. We’re excited to see this workflow power autonomous vehicles NVIDIA DRIVE and robotics NVIDIA Robotics development teams move faster with higher accuracy. 

🔗 Read the full technical breakdown: https://lnkd.in/gTy5-TNF

Dave on Data

The Dave on Data mission is to empower any professional (or team) with the DIY data science skills needed to unleash the power of AI technologies like Copilot in Excel.

What gets left out of the AI Hype Cycle is this:

AI will make you (or your team) wildly more productive.

**BUT**

You must have the requisite skills to make the most of AI.

**AND**

If these skills are lacking, you will not be able to recognize (and correct) the AI when it makes mistakes.

BTW - AI makes mistakes all the time.

Take Microsoft's Copilot in Excel AI as an example.

The "magical" scenarios where Copilot analyzes data using a few clicks and a couple of short prompts rely heavily on two things:

Python
Machine learning

Here's the thing, however. 

I've tested Copilot in Excel, which rarely generates the correct Python/machine learning code.

As the DIY data scientist, this is where you unleash Copilot's power.

I can teach you these DIY data science skills.

Regardless of role. Regardless of background.

Founder

TDWI

I develop and deliver live training experiences on data science topics such as data analysis and predictive analytics (e.g., machine learning). I focus on accelerating the data science journey for teams and organizations using a practical hands-on approach.

Training can be delivered virtually or in person with your team. The following offerings are certified by TDWI and can be taught using R or Python:

👉 Machine Learning Bootcamp
👉 Visual Data Analysis
👉 Linear/Logistic Regresion

💻 Learn more: https://daveondata.com/live-analytics-training

Data Science Consultant & Instructor

Schedulicity

VP of Analytics

Data Science Dojo

VP of Data Science

Microsoft

Sr. Director, BI and Analytics

Principal Program Manager

Sr. Director, Platform Architecture

Principal Architect

Ascentium Corp

Associate Partner, Solution Architect

Safeco Insurance

IT Architect

e-software, Inc.

Software Design Engineer

Programmer Analyst

I help ANY professional or team have more impact using data. Analytics demystified.

Want to differentiate yourself at work with Excel skills? Leaders aren't excited about this in 2025:

- Using PivotTables
- Knowing many Excel functions

You know what they're excited about: AI

And that means Copilot in Excel.

Here are the 4 steps to build the skills you need to master Copilot in Excel and impress your manager, business stakeholders, and executives:

1) Ignore "prompt engineering."
2) Learn Python.
3) Learn DIY data science.
4) Recognize hallucinations.

I want to help you own the future of Microsoft Excel.

I will help you get started today - for free.

Join 1,000s of professionals building skills for the future: 
https://daveondata.com/newsletter

David Langer

Interesting behavior from Copilot in Excel. Just another example of how Python in Excel skills are part of Excel's AI-powered future.

I was working on the next issue of my LinkedIn newsletter, which will cover using AI to build better forecasts in Microsoft Excel, and asked Copilot to create a forecast for me.

I was surprised to see that Copilot didn't use Excel's FORECAST.ETS() function because that's the best way to build data-driven forecasts using native Excel features.

Instead, Copilot in Excel generated Python code in the background to build an ETS model similar to what would be produced from FORECAST.ETS() using Python's mighty statsmodels library.

BTW - I covered statsmodels in my last two LinkedIn newsletter articles.

I'm betting that the new Copilot in Excel Agent Mode will be able to manipulate worksheets (e.g., generating formulas) directly and will be able to generate forecasts using FORECAST.ETS().

However, I'm also betting the Agent Mode will eventually be smart enough to recognize when a better forecasting technique is available from Python and use that instead.

Which means that the AI-powered future of Microsoft Excel will belong to those professionals who develop Python skills.

Stay healthy and happy data sleuthing!

#Excel #PythonInExcel #MicrosoftExcel

I help professionals and teams build better forecasts using machine learning with Python and Python in Excel.

taplio

The Battle

Harpreet Sahota 🥑

David Langer

Followers

Posts

Engagements

Likes

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance

Performance ScoreDavid Langer's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Harpreet Sahota 🥑

David Langer

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Harpreet Sahota 🥑's LinkedIn Performance

Performance ScoreDavid Langer's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance