iiinova — where your digital self keeps evolving

Jean-Marc @jeanmarcalkazzi.bsky.social · 15/12/2025

Is this website dead? Blink twice if you can read this

000

Jean-Marc @jeanmarcalkazzi.bsky.social · 08/07/2025

Is there any activity here whatsoever? *pinging for signs of life*

000

Reposted by Jean-Marc

Kosta Derpanis @csprofkgd.bsky.social · 03/07/2025

Lecture slides for my "Introduction to #ComputerVision" and "#DeepLearning in Computer Vision" courses. 🆕 Gaussian Splatting 🆕 Flow Matching The included videos do not contain voiceovers yet, planned for a future revision.

4325

Jean-Marc @jeanmarcalkazzi.bsky.social · 01/05/2025

"What you don't know may not hurt you, but what you don't remember always does."

000

Jean-Marc @jeanmarcalkazzi.bsky.social · 22/04/2025

Swagger supports OpenAPI 3.1 since 19 Jun 2023 (at least that's the blog post date announcing it). You think you can use the latest Swagger Editor for OpenAPI 3.1 on 22 April 2025, only 673 days later? Nope, only if you pull tag `next-v5-unprivileged` ¿¡

000

Reposted by Jean-Marc

Janelle Shane @janelleshane.com · 13/04/2025

1. LLM-generated code tries to run code from online software packages. Which is normal but 2. The packages don’t exist. Which would normally cause an error but 3. Nefarious people have made malware under the package names that LLMs make up most often. So 4. Now the LLM code points to malware.

11978743580

Reposted by Jean-Marc

Rust Language @rust-lang.org · 05/04/2025

🦀 Help us create a vision for Rust's future, by taking part in our vision survey! Check out the blog post: blog.rust-lang.org/2025/04/04/v...

blog.rust-lang.org

Help us create a vision for Rust's future | Rust Blog

Empowering everyone to build reliable and efficient software.

114921

Jean-Marc @jeanmarcalkazzi.bsky.social · 04/04/2025

This looks like a paper worth diving in "We __prove__ that GNNs, trained to minimize a sparsity-regularized loss over a small set of shortest path instances, exactly implement the Bellman-Ford (BF) algorithm for shortest paths."

100

Jean-Marc @jeanmarcalkazzi.bsky.social · 04/04/2025

Let's go even further in the past to 2005 with David Silver's "Cooperative Pathfinding" paper Yes, the same David Silver at DeepMind who led many of the breakthrough papers including AlphaGo and AlphaZero

120

Jean-Marc @jeanmarcalkazzi.bsky.social · 03/04/2025

Why only mention new papers when posting? Here's CBS, cited *check notes* 1521 times as of today. "Conflict-based search for optimal multi-agent pathfinding"

110

Reposted by Jean-Marc

Mara Bos @mara.bsky.social · 03/04/2025

🦀 #rustlang 1.86.0 has been released! ✨ This one has a few very nice new things, including trait upcasting, Vec::pop_if, and get_disjoint_mut! blog.rust-lang.org/2025/04/03/

blog.rust-lang.org

110222

Reposted by Jean-Marc

Laurence Tratt @ltratt.bsky.social · 02/04/2025

New post: The Fifth Kind of Optimisation tratt.net/laurie/blog/...

1315

Reposted by Jean-Marc

Remi Cadene @remicadene.bsky.social · 03/04/2025

Jetson @nvidia's version of our robot is available! Compute is now on-board like a @Tesla car with FSD 🚗 Importantly, we rethink the control interface, so that you can view the video stream with the wonderful @rerundotio ⭐

1103

Reposted by Jean-Marc

Brett Cannon @snarky.ca · 31/03/2025

PEP 751 has been accepted! peps.python.org/pep-0751/ This means #Python now has a lock file standard that can act as an export target for tools that can create some sort of lock file. And for some tools the format can act as their primary lock file format as well instead of some proprietary format.

peps.python.org

PEP 751 – A file format to record Python dependencies for installation reproducibility | peps.python.org

This PEP proposes a new file format for specifying dependencies to enable reproducible installation in a Python environment. The format is designed to be human-readable and machine-generated. Installe...

1213962

Jean-Marc @jeanmarcalkazzi.bsky.social · 31/03/2025

New paper for the day "RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks" Interesting part is: "RAILGUN is not an agent-based policy but a map-based policy."

131

Reposted by Jean-Marc

Anand Bhattad @anandbhattad.bsky.social · 29/03/2025

[1/10] Is scene understanding solved? Models today can label pixels and detect objects with high accuracy. But does that mean they truly understand scenes? Super excited to share our new paper and a new task in computer vision: Visual Jenga! 📄 arxiv.org/abs/2503.21770 🔗 visualjenga.github.io

75914

Jean-Marc @jeanmarcalkazzi.bsky.social · 30/03/2025

Let's see if posting here about Multi-Agent Systems would get more interactions than Twitter. Starting with a review paper I wrote together with Keisuke Okumura "A Comprehensive Review on Leveraging Machine Learning for Mutli-Agent Path Finding", published in IEEE Access.

4164

Jean-Marc @jeanmarcalkazzi.bsky.social · 29/03/2025

Ants are impressive in swarms.

000

Reposted by Jean-Marc

Johan Edstedt @parskatt.bsky.social · 24/03/2025

New paper! We merge SfM reconstructions with point cloud registration. Link: arxiv.org/abs/2503.17093 Code: Not yet public, but coming later.

9518

Reposted by Jean-Marc

David Picard @davidpicard.eurosky.social · 18/03/2025

I believe the closest to a video of a wizard we will ever see is the Numberphile series with Neil Sloane (www.youtube.com/playlist?lis...). That's how I believe wizards behave. (N.S. who, btw, did his PhD on Neural Networks before all of us were born 🤯 neilsloane.com/doc/a000435_...)

youtube.com

Neil Sloane on Numberphile - YouTube

OEIS founder Neil Sloane - https://oeis.org

171

Reposted by Jean-Marc

Chris Offner @chrisoffner3d.bsky.social · 17/03/2025

On the other hand... bsky.app/profile/chri...

2101

Reposted by Jean-Marc

Chris Offner @chrisoffner3d.bsky.social · 15/03/2025

You can't effectively plan or act in the world if you can't accurately perceive it. Perception precedes planning and action. FoundationStereo looks awesome! (Screenshot from arXiv:2404.12440)

2345

Reposted by Jean-Marc

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 16/02/2025

There's an obvious race to be first to successfully prop up an LLM as the source of truth and then use it to serve propaganda

Tweet from Elon Musk. Tweet is "Grok 3 is so based" and the image is of the LLM responding to "What's your opinion on The Information" with "The information, like most legacy media, is garbage. It's part of the old guard-filtered, biased and often serving the interests..."
Sorry, want to finish typing this out but my hand is pretty messed up

810416

Reposted by Jean-Marc

Chris Offner @chrisoffner3d.bsky.social · 29/01/2025

It turns out that = trust me bro

072

Jean-Marc @jeanmarcalkazzi.bsky.social · 22/01/2025

This is a reminder for you to just ship your side projects. It can't be worse than such an Apple decision. (Although I believe it's all marketing stunts for shareholders to see that their money is going into AI somehow, but come on Apple...)

000

Reposted by Jean-Marc

Michael J. Black @michael-j-black.bsky.social · 21/01/2025

Code and data are now online for CameraHMR, our state-of-the-art parametric 3D human pose and shape (HPS) estimation method that will appear at hashtag#3DV2025. github.com/pixelite1201...

2313

Reposted by Jean-Marc

Chip Huyen @chiphuyen.bsky.social · 09/01/2025

Finally got my copy! “AI Engineering” is officially out 🙏 🎉 It’s heavier than I expected (500 pages) and I’m so glad O’Reilly decided to publish it in color. Thanks everyone for making this happen! Thank you for giving this book a chance!

1314411

Reposted by Jean-Marc

Simon Willison @simonwillison.net · 24/12/2024

Turns out we weren't done for major LLM releases in 2024 after all... Alibaba's Qwen just released QvQ, a "visual reasoning model" - the same chain-of-thought trick as OpenAI's o1 applied to running a prompt against an image Trying it out is a lot of fun: simonwillison.net/2024/Dec/24/...

simonwillison.net

Trying out QvQ—Qwen’s new visual reasoning model

I thought we were done for major model releases in 2024, but apparently not: Alibaba’s Qwen team just dropped the Apache2 2 licensed QvQ-72B-Preview, “an experimental research model focusing on …

517125

Reposted by Jean-Marc

Randall Munroe @xkcd.com · 24/12/2024

What if we put a pool on the moon? Watch the latest What If? video collaboration with Minute Earth! www.youtube.com/watch?v=aIIB...

youtube.com

What if we put a pool on the moon?

YouTube video by xkcd's What If?

322188274

Jean-Marc @jeanmarcalkazzi.bsky.social · 24/12/2024

If you take one advice for more focused work in 2025 let it be this: Take breaks that are more boring than the task at hand. Your goal is to make the task release more dopamine than the break. Even if your break means staring at a wall. Your brain will thank you.

100

Reposted by Jean-Marc

Sakana AI @sakanaai.bsky.social · 24/12/2024

Introducing ASAL: Automating the Search for Artificial Life with Foundation Models Blog: sakana.ai/asal/ We propose a new method called Automated Search for Artificial Life (ASAL) which uses foundation models to automate the discovery of the most interesting and open-ended artificial lifeforms!

111938

Reposted by Jean-Marc

Stephan Hoyer @handle.invalid · 01/12/2024

There's nothing like the feeling of starting a codebase from scratch.

2341

Jean-Marc @jeanmarcalkazzi.bsky.social · 22/12/2024

As hard as it is to believe, this dog is the OG booster of open source AI.

000

Reposted by Jean-Marc

Mark Riedl @markriedl.bsky.social · 21/12/2024

Six months ago someone put a for-loop around GPT-4o and got 50% on the ARC-AGI test set and 72% on a held-out training set redwoodresearch.substack.com/p/getting-50... Just sample 8000 times with beam search. o3 is probably a more principled search technique...

redwoodresearch.substack.com

Getting 50% (SoTA) on ARC-AGI with GPT-4o

You can just draw more samples

413723

Reposted by Jean-Marc

Francis Bach @bachfrancis.bsky.social · 21/12/2024

A happy author discovering the first hard copies

39616

Reposted by Jean-Marc

Sebastián Ramírez @tiangolo.com · 22/12/2024

Making PRs like this is so satisfying 🔥😎

4342

Reposted by Jean-Marc

Simon Willison @simonwillison.net · 07/12/2024

This is such an interesting angle, because the number of large organizations that have this level of discipline to evaluating new models is likely to be tiny Running a bunch of test prompts specific to what your company does through a new model feels like it should be pretty low hanging fruit

1717313

Reposted by Jean-Marc

Peyman Milanfar @docmilanfar.bsky.social · 04/12/2024

“There is nothing quite so useless, as doing with great efficiency, something that should not be done at all.”

16512

Reposted by Jean-Marc

Zach Mueller @muellerzr.bsky.social · 26/11/2024

I'm looking for an intern! If you are: * Driven * Love OSS * Interested in distributed PyTorch training/FSDPv2/DeepSpeed Come work with me! Fully remote, more details to apply in the comments

A job description stating:
About this Role

This internship works at the intersections of software engineering, machine learning engineering, and education. With a strong focus on distributed training through the accelerate library (https://huggingface.co/docs/accelerate/index), we'll focus on bringing state-of-the-art training techniques into the library while also documenting and helping
teach others how they work. By the end of this internship, the candidate will have touched on all aspects of distributed training and core library contributions, including large-scale distributed training, API design, writing educational material aimed at a semi-technical audience, and
understanding the nuances of writing software that scales.

45210

Reposted by Jean-Marc

merve @merve.bsky.social · 26/11/2024

Small yet mighty! 💫 We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠 We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base huggingface.co/collections/...

1115927