Guillaume Dalle
@gdalle.bsky.social
Researcher in machine learning and optimization. Open source enthusiast. Parody songwriter (aka PianoHamster). OCD survivor.
Note to self: create a second Spotify account to work on song covers. Maybe this will allow my end-of-year recap to not look like an obsessive French pop fever dream.
December 3, 2025 at 3:21 PM
Note to self: create a second Spotify account to work on song covers. Maybe this will allow my end-of-year recap to not look like an obsessive French pop fever dream.
Reposted by Guillaume Dalle
Awesome to see the French government recognize our work on open-source software! @ouvrirlascience.bsky.social
My baby #JuliaLang package got an award!
DifferentiationInterface.jl just received a national prize for open-source research software and I couldn't be prouder. We started this from a vague dream with @adrianhill.de, and reached 1000 dependents and 100k downloads last month.
Research != just papers.
DifferentiationInterface.jl just received a national prize for open-source research software and I couldn't be prouder. We started this from a vague dream with @adrianhill.de, and reached 1000 dependents and 100k downloads last month.
Research != just papers.
December 2, 2025 at 7:03 PM
Awesome to see the French government recognize our work on open-source software! @ouvrirlascience.bsky.social
My baby #JuliaLang package got an award!
DifferentiationInterface.jl just received a national prize for open-source research software and I couldn't be prouder. We started this from a vague dream with @adrianhill.de, and reached 1000 dependents and 100k downloads last month.
Research != just papers.
DifferentiationInterface.jl just received a national prize for open-source research software and I couldn't be prouder. We started this from a vague dream with @adrianhill.de, and reached 1000 dependents and 100k downloads last month.
Research != just papers.
December 2, 2025 at 9:55 AM
My baby #JuliaLang package got an award!
DifferentiationInterface.jl just received a national prize for open-source research software and I couldn't be prouder. We started this from a vague dream with @adrianhill.de, and reached 1000 dependents and 100k downloads last month.
Research != just papers.
DifferentiationInterface.jl just received a national prize for open-source research software and I couldn't be prouder. We started this from a vague dream with @adrianhill.de, and reached 1000 dependents and 100k downloads last month.
Research != just papers.
Trying to learn Rust for the Advent of Code, and literally every page of the manual has me going “wow, that *is* a problem I encountered in other languages and what a clever way to solve it”.
November 30, 2025 at 1:35 PM
Trying to learn Rust for the Advent of Code, and literally every page of the manual has me going “wow, that *is* a problem I encountered in other languages and what a clever way to solve it”.
Reposted by Guillaume Dalle
Yes!!!
This is what prompted me to write the following paper:
dl.acm.org/doi/full/10....
A lot is explained by narratives and social norms driving research.
We need to build our own narratives, as a research community, this is what we do
This is what prompted me to write the following paper:
dl.acm.org/doi/full/10....
A lot is explained by narratives and social norms driving research.
We need to build our own narratives, as a research community, this is what we do
Hype, Sustainability, and the Price of the Bigger-is-Better Paradigm in AI | Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency
dl.acm.org
November 29, 2025 at 7:58 AM
Yes!!!
This is what prompted me to write the following paper:
dl.acm.org/doi/full/10....
A lot is explained by narratives and social norms driving research.
We need to build our own narratives, as a research community, this is what we do
This is what prompted me to write the following paper:
dl.acm.org/doi/full/10....
A lot is explained by narratives and social norms driving research.
We need to build our own narratives, as a research community, this is what we do
Don't mind me, just going through old, irrelevant posts
OpenReview? More like BrokenReview, amirite?
November 28, 2025 at 6:54 AM
Don't mind me, just going through old, irrelevant posts
Reposted by Guillaume Dalle
each poster session at #neurips2025 has about 1000 posters. stupid question but isn't that too much?
November 27, 2025 at 5:11 AM
each poster session at #neurips2025 has about 1000 posters. stupid question but isn't that too much?
Monotone operator theory be like: every algorithm is a fixed-point algorithm. A strangely comforting idea.
November 25, 2025 at 10:26 AM
Monotone operator theory be like: every algorithm is a fixed-point algorithm. A strangely comforting idea.
⚠️ WANTED: PhD student ⚠️
The topic? GPU-friendly algorithms for discrete optimization and mathematical programming, to be used inside decision-focused learning pipelines.
The mentors? My colleague Axel Parmentier and myself.
[1/3]
The topic? GPU-friendly algorithms for discrete optimization and mathematical programming, to be used inside decision-focused learning pipelines.
The mentors? My colleague Axel Parmentier and myself.
[1/3]
November 21, 2025 at 4:52 PM
⚠️ WANTED: PhD student ⚠️
The topic? GPU-friendly algorithms for discrete optimization and mathematical programming, to be used inside decision-focused learning pipelines.
The mentors? My colleague Axel Parmentier and myself.
[1/3]
The topic? GPU-friendly algorithms for discrete optimization and mathematical programming, to be used inside decision-focused learning pipelines.
The mentors? My colleague Axel Parmentier and myself.
[1/3]
Claude poets society
November 21, 2025 at 12:01 AM
Claude poets society
Teaching a class on decomposition methods for MILPs tomorrow and I'm wondering what the modern alternative is for "master problem" (as opposed to the pricing subproblem). Any suggestions? I've been using "main problem" but it feels too generic.
November 19, 2025 at 12:49 PM
Teaching a class on decomposition methods for MILPs tomorrow and I'm wondering what the modern alternative is for "master problem" (as opposed to the pricing subproblem). Any suggestions? I've been using "main problem" but it feels too generic.
Note to self: in the future, check the author names twice *before* sending review invitations.
This lesson is sponsored by the Shameful Society of New Action Editors who Invited Authors to Review their Own Paper.
This lesson is sponsored by the Shameful Society of New Action Editors who Invited Authors to Review their Own Paper.
November 8, 2025 at 6:30 PM
Note to self: in the future, check the author names twice *before* sending review invitations.
This lesson is sponsored by the Shameful Society of New Action Editors who Invited Authors to Review their Own Paper.
This lesson is sponsored by the Shameful Society of New Action Editors who Invited Authors to Review their Own Paper.
OpenReview? More like BrokenReview, amirite?
November 7, 2025 at 11:57 AM
OpenReview? More like BrokenReview, amirite?
Gotta love how objectively insane it is that we even have to say this out loud.
📢🚨Folks, you can only submit 25 papers this year to CVPR (25 submissions per author cap). So, please plan accordingly.
November 4, 2025 at 8:29 PM
Gotta love how objectively insane it is that we even have to say this out loud.
Doing my first reviewer assignment as an editor, and I can officially confirm: we need fewer papers and more reviewers.
November 3, 2025 at 9:17 PM
Doing my first reviewer assignment as an editor, and I can officially confirm: we need fewer papers and more reviewers.
Happy to announce that I joined the crew of @tmlrorg.bsky.social as an action editor 📝
We need a publication model with the fast turnaround of ML conferences but no attendance requirement and less reviewer lottery. I believe TMLR is part of the solution, and if you do too, come review with us!
We need a publication model with the fast turnaround of ML conferences but no attendance requirement and less reviewer lottery. I believe TMLR is part of the solution, and if you do too, come review with us!
October 28, 2025 at 12:42 PM
Happy to announce that I joined the crew of @tmlrorg.bsky.social as an action editor 📝
We need a publication model with the fast turnaround of ML conferences but no attendance requirement and less reviewer lottery. I believe TMLR is part of the solution, and if you do too, come review with us!
We need a publication model with the fast turnaround of ML conferences but no attendance requirement and less reviewer lottery. I believe TMLR is part of the solution, and if you do too, come review with us!
I’m recruiting a postdoctoral researcher on a fully funded 2-year contract. The topic is developing and implementing new parallel graph algorithms, with applications to data-driven transportation and logistics.
Details and application procedure below ⬇️ Reach out if you have any questions!
Details and application procedure below ⬇️ Reach out if you have any questions!
acme-mobidec.github.io
October 27, 2025 at 5:43 PM
I’m recruiting a postdoctoral researcher on a fully funded 2-year contract. The topic is developing and implementing new parallel graph algorithms, with applications to data-driven transportation and logistics.
Details and application procedure below ⬇️ Reach out if you have any questions!
Details and application procedure below ⬇️ Reach out if you have any questions!
Reposted by Guillaume Dalle
Désolé c'était trop tentant.
www.youtube.com/watch?v=pUNM...
www.youtube.com/watch?v=pUNM...
Sarko, libre dans sa tête
YouTube video by PianoHamster
www.youtube.com
October 23, 2025 at 4:45 PM
Désolé c'était trop tentant.
www.youtube.com/watch?v=pUNM...
www.youtube.com/watch?v=pUNM...
Désolé c'était trop tentant.
www.youtube.com/watch?v=pUNM...
www.youtube.com/watch?v=pUNM...
Sarko, libre dans sa tête
YouTube video by PianoHamster
www.youtube.com
October 23, 2025 at 4:45 PM
Désolé c'était trop tentant.
www.youtube.com/watch?v=pUNM...
www.youtube.com/watch?v=pUNM...
Reposted by Guillaume Dalle
I’m reasonably confident that this is the first Disney song cover about machine learning conferences.
At least the first one so far.
Don’t tempt me.
#MLSky
youtu.be/kWkgl9Mb2p4?...
At least the first one so far.
Don’t tempt me.
#MLSky
youtu.be/kWkgl9Mb2p4?...
San Diego
YouTube video by PianoHamster
youtu.be
October 20, 2025 at 11:29 AM
I’m reasonably confident that this is the first Disney song cover about machine learning conferences.
At least the first one so far.
Don’t tempt me.
#MLSky
youtu.be/kWkgl9Mb2p4?...
At least the first one so far.
Don’t tempt me.
#MLSky
youtu.be/kWkgl9Mb2p4?...
I’m reasonably confident that this is the first Disney song cover about machine learning conferences.
At least the first one so far.
Don’t tempt me.
#MLSky
youtu.be/kWkgl9Mb2p4?...
At least the first one so far.
Don’t tempt me.
#MLSky
youtu.be/kWkgl9Mb2p4?...
San Diego
YouTube video by PianoHamster
youtu.be
October 20, 2025 at 11:29 AM
I’m reasonably confident that this is the first Disney song cover about machine learning conferences.
At least the first one so far.
Don’t tempt me.
#MLSky
youtu.be/kWkgl9Mb2p4?...
At least the first one so far.
Don’t tempt me.
#MLSky
youtu.be/kWkgl9Mb2p4?...
JuliaCon Local Paris 2025 is a wrap! Thank you so much to all of our attendees and presenters, who made this conference a wonderful mix of software and science.
Next step: watch out for the talk recordings on YouTube... and see you next year in Germany!
www.youtube.com/playlist?lis...
Next step: watch out for the talk recordings on YouTube... and see you next year in Germany!
www.youtube.com/playlist?lis...
October 17, 2025 at 3:53 PM
JuliaCon Local Paris 2025 is a wrap! Thank you so much to all of our attendees and presenters, who made this conference a wonderful mix of software and science.
Next step: watch out for the talk recordings on YouTube... and see you next year in Germany!
www.youtube.com/playlist?lis...
Next step: watch out for the talk recordings on YouTube... and see you next year in Germany!
www.youtube.com/playlist?lis...
Periodic appreciation post for this gem of a review by Hannah Bast and coauthors. If you think you know how to compute shortest paths... trust me, you don't. I can give you one spoiler though: preprocessing the graph helps A LOT.
doi.org/10.1007/978-...
doi.org/10.1007/978-...
October 13, 2025 at 3:40 PM
Periodic appreciation post for this gem of a review by Hannah Bast and coauthors. If you think you know how to compute shortest paths... trust me, you don't. I can give you one spoiler though: preprocessing the graph helps A LOT.
doi.org/10.1007/978-...
doi.org/10.1007/978-...
Me this morning in front of a class: “So Euler wanted to cross all 7 bridges exactly once during his stroll…”
An inquisitive high school student: “Was Euler smoking opium?”
An inquisitive high school student: “Was Euler smoking opium?”
October 9, 2025 at 3:10 PM
Me this morning in front of a class: “So Euler wanted to cross all 7 bridges exactly once during his stroll…”
An inquisitive high school student: “Was Euler smoking opium?”
An inquisitive high school student: “Was Euler smoking opium?”
Reposted by Guillaume Dalle
The European open-source community is growing, and it's only the beginning! See you all in Paris 🥐
JuliaCon Local Paris starts tomorrow 🤩 Which part of our amazing program are you most excited about?
#JuliaLang @juliacon.bsky.social @julialang.org
#JuliaLang @juliacon.bsky.social @julialang.org
October 1, 2025 at 10:18 AM
The European open-source community is growing, and it's only the beginning! See you all in Paris 🥐