Thien Le retweeted
Proof of the 40-year old Bandelt-Dress conjecture on the maximum quartet distance between phylogenetic trees (and an interesting connection to independence testing). arxiv.org/abs/2608.03542
Thien Le retweeted
Exciting result: k-Coloring is in (2-eps_k)^n time, where eps_k>0 for every fixed k!
Algorithms faster than the 2^n time needed to compute the chromatic number were previously known only for k<=6.
arxiv.org/abs/2607.25973
Thien Le retweeted
It's been wild to see our work on Muon and the anthology start to get scaled up by the big labs.
After @Kimi_Moonshot released Moonlight, people have asked whether Muon is compatible with muP. I wanted to write up an explainer, as there is something deeper going on here!
(1/8)
Thien Le retweeted
Are you canonicalizing your data? Depending on the group, you might be unavoidably introducing discontinuity...but there's a fix!
Come to our ICML poster, #511, on Wednesday 1:30 - 3:00 PM to hear more! Joint work with Nadav Dym and Jonathan Siegel
arxiv.org/pdf/2402.16077
Thien Le retweeted
Looking forward to mentoring a project at this great summer school! Students interested in GNNs / geometric deep learning should consider applying 😀
🌟Applications open - LOGML 2024🌟
👥 Mentor-led projects, expert talks, tutorials, socials, and a networking night
📝 Application form: logml.ai/
📅 Apply by 26 Jan 2024 📝
📩 Questions? [email protected]
#LOGML #Geometry #MachineLearning #SummerSchool
Thien Le retweeted
yufeizhao.com/blog/2023/12/2…
I’m delighted to showcase and celebrate a selection of recent papers by the talented combinatorialists at MIT, especially those by students and postdocs. These papers reflect the culmination of their hard work, dedication, and innovative problem solving.
Thien Le retweeted
I'll be presenting our work on optimal approximation algorithms for combinatorial problems with graph neural nets at the Mathematics of Modern Machine Learning (M3L) workshop. Saturday 4pm, room 242!
Arxiv: arxiv.org/abs/2310.00526
Thien Le retweeted
Excited to present this work on Wednesday! Also, if you’re at NeurIPS and want to chat about equivariant learning, AI for science, or anything else, don’t hesitate to reach out 😄
We will be presenting our work at the poster session on Wednesday from 5 to 7 p.m. CST, so come check it out if you're interested in AI4Science and/or Self-Supervised learning 😉
Paper link: openreview.net/forum?id=ZULq…
