Jean-Marc
@jeanmarcalkazzi.bsky.social
I like to solve meaningful problems. Applied AI @ idealworks , Previously InnovationLab @ BMWGroup.
Is there any activity here whatsoever?
*pinging for signs of life*
*pinging for signs of life*
July 8, 2025 at 6:38 AM
Is there any activity here whatsoever?
*pinging for signs of life*
*pinging for signs of life*
Reposted by Jean-Marc
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.
🆕 Gaussian Splatting
🆕 Flow Matching
The included videos do not contain voiceovers yet, planned for a future revision.
July 3, 2025 at 3:09 PM
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.
🆕 Gaussian Splatting
🆕 Flow Matching
The included videos do not contain voiceovers yet, planned for a future revision.
"What you don't know may not hurt you, but what you don't remember always does."
May 1, 2025 at 10:35 AM
"What you don't know may not hurt you, but what you don't remember always does."
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` ¿¡
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` ¿¡
April 22, 2025 at 1:53 PM
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` ¿¡
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` ¿¡
Reposted by Jean-Marc
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.
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.
LLMs hallucinating nonexistent software packages with plausible names leads to a new malware vulnerability: "slopsquatting."
LLMs can't stop making up software dependencies and sabotaging everything
: Hallucinated package names fuel 'slopsquatting'
www.theregister.com
April 12, 2025 at 11:43 PM
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.
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.
Reposted by Jean-Marc
Reposted by Jean-Marc
🦀 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...
Check out the blog post: blog.rust-lang.org/2025/04/04/v...
Help us create a vision for Rust's future | Rust Blog
Empowering everyone to build reliable and efficient software.
blog.rust-lang.org
April 5, 2025 at 10:52 AM
🦀 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...
Check out the blog post: blog.rust-lang.org/2025/04/04/v...
Reposted by Jean-Marc
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."
"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."
April 4, 2025 at 8:16 PM
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."
"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."
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
Yes, the same David Silver at DeepMind who led many of the breakthrough papers including AlphaGo and AlphaZero
April 4, 2025 at 6:09 AM
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
Yes, the same David Silver at DeepMind who led many of the breakthrough papers including AlphaGo and AlphaZero
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"
Here's CBS, cited *check notes* 1521 times as of today.
"Conflict-based search for optimal multi-agent pathfinding"
April 3, 2025 at 8:46 PM
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"
Here's CBS, cited *check notes* 1521 times as of today.
"Conflict-based search for optimal multi-agent pathfinding"
Reposted by Jean-Marc
🦀 #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/
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
April 3, 2025 at 10:13 AM
🦀 #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/
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/
Reposted by Jean-Marc
New post: The Fifth Kind of Optimisation tratt.net/laurie/blog/...
April 2, 2025 at 10:25 AM
New post: The Fifth Kind of Optimisation tratt.net/laurie/blog/...
Reposted by Jean-Marc
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 ⭐
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 ⭐
April 3, 2025 at 7:01 AM
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 ⭐
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 ⭐
Reposted by Jean-Marc
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.
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.
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...
peps.python.org
March 31, 2025 at 9:28 PM
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.
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.
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."
"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."
March 31, 2025 at 2:53 PM
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."
"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."
Reposted by Jean-Marc
[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
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
March 29, 2025 at 7:36 PM
[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
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
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.
"A Comprehensive Review on Leveraging Machine Learning for Mutli-Agent Path Finding", published in IEEE Access.
March 30, 2025 at 2:51 PM
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.
"A Comprehensive Review on Leveraging Machine Learning for Mutli-Agent Path Finding", published in IEEE Access.
Ants are impressive in swarms.
March 29, 2025 at 1:07 PM
Ants are impressive in swarms.