Reposted by Amine El OuassouliMargot Finn @eicathomefinn.bsky.social · 09/04/2025'Bluesky has overtaken its flailing rival X in hosting posts related to new academic research, indicating the platform is fast becoming the go-to place for scholars to share their work.'timeshighereducation.comX’s dominance ‘over’ as Bluesky becomes new hub for researchData indicates more scholars turning to alternative social media site to post about their work after Elon Musk’s Twitter takeover 129174334388
Amine El Ouassouli @aelouass.bsky.social · 06/03/202513 minutes of wisdom. “No authorities in science”. Amen to that. 020
Amine El Ouassouli @aelouass.bsky.social · 18/02/2025@jfoerst.bsky.social take on how the community sees the ARC Challenge and how we evaluate models and use benchmarks nowadays is 👌. #more_science_less_hype (please). PS: Amazing discussion and good brain food, as usual with MLST.youtube.comImageNet Moment for Reinforcement Learning?YouTube video by Machine Learning Street Talk 031
Amine El Ouassouli @aelouass.bsky.social · 30/01/2025I missed this one when it came out but I can tell that it is one of the most useful piece of research I’ve read in a while. “GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models” arxiv.org/html/2410.05...arxiv.orgGSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models 100
Amine El Ouassouli @aelouass.bsky.social · 24/01/2025We really need better brain-power allocation. The current algorithm is kind of turning crazy. 000
Amine El Ouassouli @aelouass.bsky.social · 16/01/2025The more I read and listen to current debates in the field, the more I’m convinced that we have a model evaluation crisis. 000
Amine El Ouassouli @aelouass.bsky.social · 11/01/2025I never understood people going to concerts to spend their time there attending through the tiny screens of their phones. 000
Amine El Ouassouli @aelouass.bsky.social · 07/01/2025Is it just me or are we in an Eliza effect pandemic? 000
Amine El Ouassouli @aelouass.bsky.social · 31/12/2024Huh, what a year ! Happy new year, everyone ! May it be a better one than 2024 (it’s not that hard, though) Take care of your loved ones. 000
Amine El Ouassouli @aelouass.bsky.social · 26/12/2024There is no ultimate benchmark. Having good results on a benchmark means that a model cracked it down. How it cracked it down shows the extent of the progress towards solving the problem=>sometimes cracking a benchmark tells you more that it is not sufficient to measure progress anymore. 100
Amine El Ouassouli @aelouass.bsky.social · 09/12/2024Definitely a good book. Not a textbook but a good resource for anyone interested in the field and have some math literacy. 031
Reposted by Amine El OuassouliEugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 09/12/2024An updated intro to reinforcement learning by Kevin Murphy: arxiv.org/abs/2412.05265! Like their books, it covers a lot and is quite up to date with modern approaches. It also is pretty unique in coverage, I don't think a lot of this is synthesized anywhere else yetarxiv.orgReinforcement Learning: An OverviewThis manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based RL, policy-gradient methods, model-based met... 926974
Amine El Ouassouli @aelouass.bsky.social · 30/11/2024I think I've got more interesting insights from here's feed in not even a week than i got from the other place's in more than a year. 010
Reposted by Amine El OuassouliChristoph Molnar @christophmolnar.bsky.social · 27/11/2024The unofficial GIF-based pandas library documentation. pandas.DataFrame.rollingmedia.tenor.coma panda bear is laying down in the grass .Alt: a panda bear is rolling down in the grass. It's a side-ways roll, hlding some type of object. I give 10/10. 3546
Amine El Ouassouli @aelouass.bsky.social · 26/11/2024I just deactivated my X account. Blsky now has exclusivity on my procrastinating scrolling activity. 010
