open source @roboflow | AI engineering at @UdeSA🇦🇷 prev founder @SatsOnFire
Joined May 2016
- Tweets3.9K
- Following1.1K
- Followers2K
- Likes19.4K
Pinned Tweet
I’m thrilled to present the KAN Convolutional Layer, a promising neural architecture for image processing. Last week KANs came out, as an alternative to the MLP. We extended this idea to Convolutional Layers, creating the KAN Convolution. Join me in this thread to more about it🧵
Alex Bodner retweeted
Puentes starts in two days!
If you want to meet any fellows, request intros here:
puentes.antigravity.capital/…
Puentes starts this Sunday.
We're flying 15 of the best young engineers from Latin America to SF.
They’re among the most talented in their countries, and they want to be here to compete with the best.
Our goal at @antigravitysf is to help them stay.
Meet the engineers 👇
How do we do to track an object accurately with a camera moving? Meet Camera Motion Compensation!
In practice, you can use BoT-SORT in trackers with a 1 line change:
github.com/roboflow/trackers
Object tracking explained in 3Blue1Brown style.
Learn about the tracking loop, kalman filters, why occlusion breaks and one way to fix it.
Try it out github.com/roboflow/trackers
Alex Bodner retweeted
Gemini 4 Argon stream in 30 minutes. see you!
Gemini 4 Argon vs GPT-6 Astra YouTube stream
tomorrow, Oct 15th, 8 AM PT / 11 AM ET / 5 PM CET
save the time and see you tomorrow
- detection
- segmentation
- transcription
- data extraction
- efficiency and cost
what else?
link: youtube.com/live/bBX_c5AFuMQ
Alex Bodner retweeted
The fellows want to meet engineers at:
@SierraPlatform
@posthog
@chaidiscovery
@linear
@WisprFlow
@AnthropicAI
@OpenAI
Instinct
@SpaceXSI
@modal
@PrimeIntellect
@ssi
@theworldlabs
@beltichq
If you work or know anyone there, dm for dinner invite :)
Puentes starts this Sunday.
We're flying 15 of the best young engineers from Latin America to SF.
They’re among the most talented in their countries, and they want to be here to compete with the best.
Our goal at @antigravitysf is to help them stay.
Meet the engineers 👇
Alex Bodner retweeted
Puentes starts this Sunday.
We're flying 15 of the best young engineers from Latin America to SF.
They’re among the most talented in their countries, and they want to be here to compete with the best.
Our goal at @antigravitysf is to help them stay.
Meet the engineers 👇
Muy contento de participar en esta edición de Puentes! Voy a estar viajando el viernes para SF, y buscando conocer gente del ecosistema. Si trabajas en AI, vision, robotica, NLP escribime!
@AlexBodner_ (22, Argentina). At 16, he co-founded Satellites On Fire and built its wildfire models and alerts (900 monthly users). He now builds Roboflow’s object tracking library (380K+ downloads, 3.9K+ stars) and is first author of Convolutional KANs (170+ citations).
My favourite thing about @roboflow Trackers is how easy we made it to swap things and create the best tracker for your case.
Swap the tracker, the IoU variant, camera motion compensation, dynamic frame rate or masks, one line change, and see what works best!
Any detector works.
Find more in:
github.com/roboflow/trackers
Leave a star if you find it useful, it motivates us🌟
I'm still working on the AutoTracking dataset creation. Now I've tried GPT-6.1 Sol on decisions a human would need to make.
Astra was good but expensive. At 1/4 of the cost, Sol performs about the same.
Stay tuned
We are trying to give a model three words and get back a labelled tracking dataset. No human labels anywhere.
After a week, its still not perfect, but the self improvement is working. Out of Astra + SAM3 we can generate some tracks that fragment, but we can use that for training cheaper models that allow us to detect players better and join tracks.
Numbers so far:
On SoccerNet's official test split, 46 clips it never saw: 62.5 HOTA.
For reference on the same clips, published baselines that use SoccerNet's labelled train split or pedestrian datasets:
- DeepSORT 36.7
- ByteTrack 47.2
- FairMOT fine-tuned on SoccerNet 57.9
We use none of those labels. Still far behind the 2023 challenge winner at 75.6.
Excited for next week progress👀
For which use case would you use this?
Alex Bodner retweeted
We’re running a personal agents hackathon the last day of Puentes!
> Only 50 engineers
> $2K in cash for the top 3 teams
> Judges like @montonenico, @iAligator, @rincidium
> Compete against all the Puentes fellows in SF
Link below. @ Saturday, Oct 25
OpenAI just posted a paper claiming to prove the quasi-Riemann hypothesis: no zero of the Riemann zeta function, or of any Dirichlet L-function, has real part above 11/12. A companion paper pushes it to 7/8.
Since Riemann's 1859 paper, nobody had proven any fixed bound like this. If it holds up, it also rules out Siegel zeros.
What this means:
The zeta function encodes how the prime numbers are distributed. Its inputs are complex numbers, so each zero has a real part and an imaginary part.
There are some trivial zeros, we dont care about them. Every other zero is known to have real part between 0 and 1. The Riemann Hypothesis says they should all have real part exactly 1/2.
Nobody has proven that. The best known bounds got closer and closer to 1 as the imaginary part grew. That weaker statement is the quasi-Riemann hypothesis, and it's what this paper claims.
Siegel zeros are hypothetical zeros extremely close to 1 that have haunted number theory for nearly a century. This result would rule them out.
Its still under experts review, but its huge!
We’re releasing a broad range of new mathematical results produced by an internal frontier model.
We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results.
github.com/openai/math
Object tracking explained in 3Blue1Brown style.
Learn about the tracking loop, kalman filters, why occlusion breaks and one way to fix it.
Try it out github.com/roboflow/trackers
Asked Opus 5.5 to explain RF-DETR like 3Blue1Brown, one shot. This is the result.
It has so much better understanding of space and explanation clarity than previous models.
What are your thoughts?
Asked Opus 5.5 to animate how object tracking works based on our blog post, but pixel art👾
This is Simple Online and Realtime Tracking (SORT), step by step. Every guess, overlap score and ID on screen comes from the real Trackers library running on this pixel pitch.
Sound on 🔊
Learn how SORT works on the blog post (written by humans): blog.roboflow.com/sort-expla…
