Has anyone ever gotten Claude or GPT to rate a paper above 5/10 for review? With so many reviews being LLM-generated (or at least LLM-inspired), it feels like you’re stuck in a never-ending cycle of borderline scores, no matter how much you improve the paper.
Preference learning typically requires large amounts of pairwise feedback to learn an adequate preference model. However, can we improve the sample-efficiency and alignment ability of preference learning with linguistic feedback? With MAPLE🍁, we can! (AAAI-25 Alignment Track)🧵
BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
Excited to be @AAMASconf!
I attended the OptLearnMas workshop today and presented our work on minimizing negative side effects on multi-agent systems.
We have the poster session tomorrow for the main conference at 29B, 12.30 PM. Happy to chat about our work!
Excited to start my 2nd semester of PhD @umasscs. I will be working as an RA under Prof. Shlomo Zilberstein. The good news is the MA cold doesn’t bother me anymore. Looking forward to a good semester ahead!
It was a really enjoyable discussion with @MilindTambe_AI and others on multi agent systems for social good at @aamas2021. Hope to see more inspiring works in the future.
Terrific idea @aamas2021 to have these informal discussion sessions with conference attendees! I really enjoyed discussing multiagent systems for social good at Stonehenge today; thx Eric Shieh, @sandhya_ai@AparnaMoumi Aravind Venugopal & many others present for contributions.
We are excited to share that we'll be going to present our paper at the @aamas2021 conference with @AparnaMoumi on May 6, 16.00 BST. Everyone is invited to the presentation and feel free to ask any questions or provide any feedback. 1/2
'We've only been here a few hours and have seen half a dozen people die while they wait for treatment.'
India has recorded more than 332,000 #COVID19 cases in a single day.
@AlexCrawfordSky reports from Delhi, where people are "begging for oxygen."
https://t.co/2DIoxqdjOz
I just realized I listed the wrong email address on my webpage. The good thing is that the wrong email address does not exist. So, if in case anybody tried to reach out, they should get a warning. 🤷♀️
I started seeing some activity on this blog post -- so figured that's a good reminder to re-share this given the upcoming #CVPR2021 rebuttal deadline :)
Keep in mind that this is just what we (@stefmlee, @DhruvBatraDB, and I) tend to follow, YMMV.
https://t.co/rXqCws81MM
I made a playlist of 11 short videos (most are 7-13 mins long) on Ethics in Machine Learning
This is from my 2 hrs ethics lecture in Practical Deep Learning for Coders v4. I thought these short videos would be easier to watch, share, or skip around
https://t.co/bLHhdPLch4
Ok, I don't have 2020 favorite papers for 2020, but I did learn a couple of things this year. Here is a slow moving thread of the ideas I learned about this year. Many of these ideas are old, but they were new to me!🧵