Profile avatar
marcelhussing.bsky.social
PhD student at the University of Pennsylvania. Currently, intern at MSR. Interested in reliable and replicable reinforcement learning and using it for knowledge discovery: https://marcelhussing.github.io/ All posts are my own.
119 posts 2,752 followers 344 following
Regular Contributor
Active Commenter
Posts 26 Comments 24

📢 Deadline Extension Alert! 📢 Good news! We’re extending the #CoLLAs2025 submission deadlines: 📝 Abstracts: Feb 26, 2025, 23:59 AoE 📄 Papers: Mar 3, 2025, 23:59 AoE More time to refine your work—don't miss this chance to contribute to #lifelong-learning research! 🚀 🔗 lifelong-ml.cc

submitted 6 days ago • 0 comments

I was very hyped about this place initially, now I come here, see 5 posts about politics, unfollow 5 people and close the website. Where are the interesting AI posts?

submitted 4 days ago • 1 comment

Can you solve group-conditional online conformal prediction with a no-regret learning algorithm? Not with vanilla regret, but -yes- with swap regret. And algorithms from the follow-the-regularized leader family (notably online gradient descent) work really well for other reasons.

submitted 9 days ago • 1 comment

Bummed out about recent politics & news drowning out AI and science you want to see on Bluesky? Well, here is a small "sky thread" (written on a ✈️) about something I recently discovered: e-values! They are an alternative to the standard p-values as a measure of statistical significance. 1/N

submitted 9 days ago • 1 comment

Throwing compute at things has proven quite powerful in other domains but until recently not as much in #ReinforcementLearning. Excited to share that out MAD-TD paper got a spotlight at #ICLR25! Check out Claas' thread on how to get the most out of your compute/data buck when training from scratch.

submitted 15 days ago • 0 comments

EC 2025 (S)PC --- lets get ready for the Super Bowl! Every time there is a first down, bid on a paper. Field goal? Bid on two. Touchdown? Bid on 5 papers (10 if its the Eagles!) At the halftime show enter your topic preferences and conflicts. Lets go birds!

submitted 18 days ago • 3 comments

🚨🚨 RLC deadline has been extended by a week! Abstract deadline is Feb. 21 with a paper deadline of Feb. 28 🚨🚨. Please spread the word!

submitted 18 days ago • 1 comment

submitted 26 days ago • 0 comments

What a future work section should be: Oh, and here is this interesting and hard open problem that someone should solve. Future work sections in empirical ML papers: We leave hyperparameter optimization for future work.

submitted 28 days ago • 1 comment

My new year's resolution is to spend more time thinking. Last year I found myself deep in the nitty gritty of creating solutions. While that is important it is also necessary to reflect and look at the bigger picture. Entering my 5th year, I will try to focus more on defining the next problems.

submitted 57 days ago • 0 comments

Apparently I'm in the top 1% of wandb users. Good or bad sign?

submitted 62 days ago • 1 comment

Reposting a postdoc opportunity in field robotics at Penn, in case anyone missed it the first time around.

submitted 66 days ago • 0 comments

Microsoft's Computational Social Science group may have the opportunity to hire one researcher Senior: 0-3 yrs post PhD jobs.careers.microsoft.com/global/en/jo... Principal: 3+ yrs post PhD jobs.careers.microsoft.com/global/en/sh... Please note: our ability to hire this season is not certain

submitted 69 days ago • 6 comments

Anyone who shills Hydra gets a retweet. Not using it borders on malpractice.

submitted 70 days ago • 1 comment

If you're interested in the history of physics on a technical level, hit up Jorge with a follow and sub to his YouTube.

submitted 74 days ago • 0 comments

With all these all you need papers around I'm starting to think that people don't actually know what I need.

submitted 75 days ago • 1 comment

Now that @mkearnsphilly.bsky.social is here, this starter pack just became the real deal. Better refollow it. go.bsky.app/21nFz12

submitted 76 days ago • 1 comment

📦 Can frontier AI transform ANY physical object from ANY input modality into a high-quality digital twin that also MOVES? Excited to share our work,Articulate-Anything 🐵, exploring how VLMs can bridge the gap between the physical and digital worlds. Website: articulate-anything.github.io

submitted 78 days ago • 1 comment

Getting ready for #NeurIPS looking forward to meeting some old and new friends! Who is gonna be around?

submitted 82 days ago • 0 comments

Reskeeting this in case it got lost over Thanksgiving. Our lab is looking for a postdoc at the intersection of robotics and computer vision!

submitted 84 days ago • 0 comments

You just finished coding an experiment and now you run it. Running does not take days but also not seconds. Let's say it takes 25 minutes. What do you do in the time?

submitted 84 days ago • 8 comments

Been seeing a lot of RL architectures use layer norms as "design choice" without elaborating why it's needed. If you are curious take a look at our paper: arxiv.org/abs/2403.05996 TLDR: Layer norms stop your critic from diverging early on and stabilize training. cc @cvoelcker.bsky.social

submitted 85 days ago • 1 comment

Super excited about this new paper on human/model collaboration via agreement protocols! Joint work with the amazing @ncollina.bsky.social @vgup.bsky.social @aaroth.bsky.social 🌸

submitted 86 days ago • 1 comment

I have been saying "I made a blueskeet" and I have been told that that is not the term but maybe it should be? Or is there another accepted other term for skeeting?

submitted 90 days ago • 1 comment

Our lab is looking for a postdoc working on multi-robot autonomy, control and perception. This may include work on combining robots with recent advances in preception such as VLMs. If you are interested or are looking for more details about the project, hit up @ericeaton.bsky.social . #Robotics

submitted 90 days ago • 1 comment

Happy Food Coma Day to all who celebrate. 🦃🥧💤

submitted 90 days ago • 0 comments