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 🥑

i've literally been waiting for years to have an OPEN SOURCE model like qwen3-vl-embedding

i tested its multimodal retrieval capabilities on a corpus of 412 short video clips and the results literally blew my mind

here are the queries i tested:

1. a cartoon guy drinks merlot wine

i like this query because we see how it can retrieve based on semantics (a cartoon), text (the label merlot), and temporal action in the video (the cartoon guy drinks the wine mid-way through the video)

2. garfield runs out of the door

semantics are awesome here, the model knows i'm talking about the cartoon character...

3. a woman in a blue dress sleeping on a red bench

the skeptic in you might think that it's retrieving just based on the red color block in the 2/3 of the video...but notice the specific part of the query "a woman in a blue dress..." and this is only shown in 3s out of the full 10s

this is such a huge release 

and it's gonna open up SO much more for multimodal video retrieval this year

on my wishlist is natural language search of pcd datasets, who gonna ship that?

you can hack around with the model using the resources below

check out the docs: here: https://lnkd.in/gh7yfBNP

and the quickstart nbhere:  https://lnkd.in/gbinsx7p

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

for those who missed it, or were there in-person and know the trouble i was facing 😆, my ODSC webinar is now live on youtube!

in this session i discuss visual ai techniques for automotive damage detection. 

i used the cardd dataset, which is a public dataset built specifically for vehicle damage analysis and demonstrated how fiftyone helps you explore, visualize, and build models to detect dents, scratches, cracks, glass shatter, tire flats, and broken lamps.

i feel like its a super practical workshop with some insightful workflows for visual AI in automotive settings, but as the creator i might be biased.

only one way to find out for yourself, watch the webinar!

https://lnkd.in/ewfz5vZD

Open video: Mastering Visual AI with Vision-Language Models & Advanced Evaluation Techniques by Harpreet Sahota on youtube.com

Mastering Visual AI with Vision-Language Models & Advanced Evaluation Techniques by Harpreet Sahota

sometimes i look back at the shit i get done and i genuinely impress myself

how teams really build Visual AI in the wild? what's the he messy reality?  

i don't know...and maybe its because nobody’s asking practitioners and compiling their answers so we can find out the landscape actually looks like. 

so, we at Voxel51 are kickin off the...

wait for it...

 State of Visual AI survey...vey...vey

for those out ther building visual AI systems i want your hot takes

what’s the hardest part about making visual ai a reality? 

let us know in this survey

it'll take you 30 minutes and is a much better use of time than baby sitting your runs and staring at your loss curves

i can't offer much beyond my heartiest thanks, but you will get early access to the full report with benchmarks, common pain points, and where you stand within the landscape. 

here's a link: https://lnkd.in/gnsADACy

MedGemma 1.5 supports detection, but for best results, you'll need to fine-tune. 

there's a kaggle competition using the model, i created a starter notebook to give you a jump start on how to fine-tune it for detection

checkout the starter notebook and additonal resources 👇🏼

cc Omar Sanseviero Megan Risdal Logan Kilpatrick

looking forward to the next meetup in boston!

Join our in-person meetup at the Microsoft Research Lab at the Massachusetts Institute of Technology in Boston, Massachusetts on Feb 18 to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Register here: https://lnkd.in/gi4kpSMB

Talks will include:

• SNAP: Towards Segmenting Anything in Any Point Cloud - Hanhui Wang at Northeastern University

• Culturally Adaptive AI - Anku R. at Massachusetts Institute of Technology

• Data Foundations for Vision-Language-Action Models - Harpreet Sahota 🥑 at Voxel51

• Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models - Sharut G. at Massachusetts Institute of Technology

• Neural Radiance Fields for Image Verification - Sage Simhon at Pasteur Labs & ISI

#computervision #ai #artificialintelligence #machinevision #machinelearning #datascience

Syed Abdul Sami Rizvi, Matthew Ebisu and 118 other attendees

View event: Feb 18 - Boston AI, ML and Computer Vision Meetup

Feb 18 - Boston AI, ML and Computer Vision Meetup

in the asu area and wanna get started with open source contributions? then don't miss this hack

On March 21, 2026, we’re hosting Agents World: Visual AI Hackathon @Arizona State University, together with Pavan Turaga 🚀 

This is a hands-on day: meet people, build with AI, eat pizza, and leave with something you created after a short workshop and a full day of hacking. 
You’ll work with the FiftyOne ecosystem and real models used in practice, like Qwen, Gemini Vision, Sharp, and more. 

If you’re an ASU student who wants to build, learn by doing, and work with real Visual AI tools, this is for you.

Registration is open:
https://lnkd.in/gBCHW5Fg

Hope to see you at ASU. I’ll be there with the amazing Voxel51 team:  Sid Mehta, Ritchie Martori, Jimmy Guerrero ! 🙌

Inspired by the amazing Hugging Face’s 2025 AI Timeline, we created one for the Fiftyone community. The FiftyOne Community Development Timeline highlights more than 131 contributions from 2025, including datasets, models, plugins, and integrations.

You can filter by type or modality and jump straight to each integration.
https://lnkd.in/ev2kpCGN

Big thanks to the entire Voxel51 community for building all of this together.
Harpreet Sahota 🥑, Daniel Gural, Paula Ramos, PhD, Jimmy Guerrero, Derek Van de Streek, Nicholas Lotz 🚀

Gonna be a great series of talks, lots of technical depth!

Chief Community Officer @ Voxel51 | Startup Advisor

Join us on Feb 18 for the Boston AI, ML and Computer Vision Meetup! Pre-registration is mandatory to clear building security - https://lnkd.in/gHtBuH49

Talks will include:

* SNAP: Towards Segmenting Anything in Any Point Cloud - Hanhui Wang at Northeastern University

* Culturally Adaptive AI - Anku R. at MIT

* Data Foundations for Vision-Language-Action Models - Harpreet Sahota 🥑 at Voxel51

* Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models - Sharut G. at MIT

* Neural Radiance Fields for Image Verification - Sage Simhon at Pasteur Labs & ISI

***********

Want to build better computer vision models? FiftyOne is an open source toolkit from Voxel51 (our Meetup sponsor) that helps you curate datasets, evaluate model performance, visualize embeddings, catch annotation errors, and eliminate duplicate images—all in one place.

“pip install fiftyone” is all it takes to get started - https://docs.voxel51.com/

#computervision #ai #artificialintelligence #machinevision
#machinelearning #datascience #physicalai

Data Whisperer ♦ Analytics Specialist & Tech Enthusiast ♦ Join My #bookaweekchallenge

⭐ I have reached the maximum connection limit of 30,000 here on LinkedIn. Please follow me instead.
📚 Follow & join my #bookaweekchallenge or #bookamonthchallenge
📍 Current resident of Madrid, Spain & native of Charlotte, North Carolina, USA

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

Greek-American based in Spain where I run a global data/AI business. International keynote speaker, award-winning educator and the Founder of Dare to Data, on a mission to help individuals and corporations take the next step in their data and AI journey. After building a successful career in Big Tech companies such as Google and Waze, I shifted my focus to scaling impact through education, training and product evangelism. Today, I'm trusted by an extensive client list of Fortune 500 and Big Tech organizations. Outside of my corporate work, I hold an Adjunct Faculty position at several universities where I lecture and lead programs on data and AI for business. I also serve as an instructor for LinkedIn Learning and host a podcast for EM360. I am bilingual (English-Spanish) and offer collaborations in both languages.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

I am a regular international speaker supporting all things data and AI, as well as women in STEM. Some of my latest involvements include:
● Guest appearances on more than 30 podcasts such as SuperDataScience, DataFramed, Alter Everything, Ken's Nearest Neighbors, How to Get An Analytics Job, Driven by Data, Humans of Data Science, Present Beyond Measure, LightsOnData & more.
● Interview features, guest lecturer, panelist and event host!
● Keynote speeches delivered regularly since 2018 across 20+ countries in-person, virtually spanning the globe, with audiences surpassing 3,000+. A few of my latest involvements include:
→ → Fund Summit 2025 in Luxembourg LU, "Regulating the Machine: How AI is Forcing a Global Rethink on Ethics & Control"
→ → National Analytics Summit 2025 in Dublin IE, "When Data Meets Design"
→ → CNG Global Pulp Conference 2025 in Istanbul TR, "Igniting Transformation with AI"
→ → QSP Summit 2024 in Porto PT, "Navigating Tomorrow in a Data-Driven, AI-First World"
→ → Nitto ATP Finals Customer Summit 2024 in Turin IT, "Unleashing AI's Power in Modern Manufacturing"
→ → Data Universe 2024 in NYC US, "When Data Meets Design"

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

For further opportunities (podcasts, events, etc.) in my interested fields, feel free to contact me directly.

The opinions stated here are my own, not those of my employers/partners/clients.

Christina Stathopoulos, MSc

Your professional headshot is often your first impression.

On platforms like LinkedIn, it quietly answers a lot of questions for you: Are you credible? Approachable? Mine attached here is showing a subtle hint into my love for books!

There is no excuse for you to still be using that at-home selfie in bad lighting or your cropped family photo 🙄

Lately I have been experimenting with InstaHeadshots to generate AI-powered headshots. And the results are impressive! But there is a big caveat that often gets missed with these tools.

AI is only as good as the data you train it on.

If you want high quality outputs, you need high quality inputs.

When I trained my model, I used a mix of strong professional headshots and everyday photos and selfies. Different lighting, expressions, outfits and contexts.

That made all the difference in how realistic and usable my final images were.

⭐ I want to clarify that I don't think AI-generated images will replace the need for photographers. Not even close. ⭐

I fully plan to keep getting professional headshots done every two to three years. A great photographer brings expertise and quality that AI cannot do on its own.

What AI tools like this do change is SCALE.

AI now gives me access to literally HUNDREDS of additional, on brand images that I can use across platforms, talks, media and more. A quantity that would be unthinkable with a traditional photoshoot, both in terms of time and cost.

If you want to experiment with it yourself, you can try it here: https://lnkd.in/e7CnHNVU
Use code CHRISTINA15 for 15% off!

(I personally love this platform because you get a preview of your images first, and only pay once you're happy with the results.)

#artificialintelligence #generativeAI #headshots #futureofwork


💙 I partnered with InstaHeadshots because I genuinely love the product, can't wait to start using my new set of headshots and wanted to spread the word so others can try too!

🔷 TL;DR Remember that better data leads to better results. Invest in good photography. Use AI to extend it.

Data & AI Evangelist | Global Keynote Speaker & Award-Winning Educator | Making data & AI work for everyone, through a responsible lens! | Join my #bookaweekchallenge 📚

taplio

The Battle

Harpreet Sahota 🥑

Christina Stathopoulos, MSc

Followers

Posts

Engagements

Likes

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance

Performance ScoreChristina Stathopoulos, MSc's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Harpreet Sahota 🥑

Christina Stathopoulos, MSc

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 ScoreChristina Stathopoulos, MSc's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance