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

I am obsessed with Machine Learning, Generative AI, LLMs, and more — and I love sharing knowledge as much as I love learning!

Chris Alexiuk

Ilya was right, we're in the Age of Research.

Recursive Language Models (RLMs) from MIT CSAIL (including Mr. DSPy himself!) is yet another banger.

The name buries the lede a bit. The real insight comes from avoiding cramming your 10M token corpus into the context window, treat the prompt as a variable in a Python REPL and let the model programmatically peek at it.

(REPL = Read-Eval-Print Loop - basically an interactive coding environment where you type code, it runs, you see the output. Think Jupyter notebooks or a Python terminal.)

Why it matters:
- Handles inputs 100x beyond context limits
- Model decides what to look at and when
- Sub-LM calls for decomposition and synthesis

It's not magic - you're still bottlenecked by attention span at every call. But giving the model control over its own context management? That's pretty dope.

Feels like fertile ground for optimization. The paper uses a fixed system prompt across all tasks - there's definitely headroom for task-specific strategies, learned routers, or even DSPy-style prompt tuning.

Remember - even if you're just starting in AI today - you're right on time.

Paper: https://lnkd.in/gTQG4JzD
Code: https://lnkd.in/gAGcRyS5

Chris "The Wiz 🪄" Alexiuk

AI @ NVIDIA - 🏗️ Build | 🚢 Ship | 🚀 Share

It's another blog - this time: All about making a Bash Agent learn some new tricks!

Problem: I want my Bash Agent to run LangGraph CLI commands - so it can spin up my Agents. 

Issue: It's not very good at it out of the box. 

Solution: Use Reinforcement Learning (with GRPO) to teach the model powering my agent how to do it.

In the tutorial, I used: 

1. NeMo Data Designer to.....design the data. NGL. 

It was easy to use, and easy to produce the data I needed - would strongly recommend. If you want to learn more, follow Eric Tramel or Johnny Greco.

2. NeMo Gym + Unsloth

Obviously a potent combination - and obviously a blast to use. NeMo Gym is way simpler than you might imagine for how POWAFUL it is. If you want to learn more about *those* tools - well, you're already following Unsloth - so Chris Wing, Wenwen Gao, and Sylendran Arunagiri are the ones to follow for Gym!

3. Our Bash agent that we created for a previous tutorial!

All told - this takes ~3hrs. to work through (but needs an 80GB GPU for right now) and while I used LangGraph Platform CLI - you could use whatever you'd like!

Dr. Greg Loughnane and I are going to talk about "Ralph Wiggum" next Wednesday, yes, really.

If you have no clue what that means: Congrats, you're on the sane part of the internet - but the event will explain why this cutely named while loop has stolen the hearts and minds of engineers 'round the interwebs.

It will also, more importantly, serve as a practical "getting started guide" for Claude Code - tailor made for 2026, and Opus 4.5.

Leveraging these tools, as I've mentioned recently, is something that no longer feels optional - but it can be a bit of an opaque process to get started with them, and so we wanted to do this event to help people get (a bit) up to speed.

It'll also, hopefully, start you down the path to become the mayor of your very own self-built Gas Town.

Given that we're a week out - what would you most like to see us cover? Let me know in the comments!

https://lnkd.in/gNzJquMk

Open video: Ralph Wiggum: Continuous Agent Loops in Claude Code on youtube.com

Ralph Wiggum: Continuous Agent Loops in Claude Code

taplio

The Battle

Harpreet Sahota 🥑

Chris Alexiuk

Followers

Posts

Engagements

Likes

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance

Performance ScoreChris Alexiuk's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Harpreet Sahota 🥑

Chris Alexiuk

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 ScoreChris Alexiuk's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance