Asst. Prof. at Khoury College of CS at Northeastern
Boston, MA
Joined February 2020
- Tweets111
- Following208
- Followers507
- Likes164
Robin Walters retweeted
Today’s the day! The Boston TAG Party starts today at 8:45am Eastern. Some day of registrations available— join us at the Curry Student Center, Northeastern University for an amazing keynote by Dr.Maurice Weiler at 9:00am! Be there or be continuously deformable to a point!
Robin Walters retweeted
The event starts tomorrow at 8am, CSC Ballroom and 2nd floor suites at northeastern! we hope to see you there!
Robin Walters retweeted
We are kicking off the Boston TAG Party at the Curry Student Center at Northeastern University tomorrow! For all the details, check out the website: tagds.com/events/tag-ds-2026
Registration is still available (for now) until we hit capacity: commerce.cashnet.com/SFTAG
@bostonsymmetry
Robin Walters retweeted
Registration for our 3-day Boston Symmetry / TagDS joint conference is open now! Check out our registration link and event details in thread. There will be contributed posters and talks, an array of invited speakers, a dinner social, and more!
Robin Walters retweeted
With author notifications around the corner we are pleased to announce that registration for the Boston TAG Party is open! commerce.cashnet.com/SFTAG
Be there or be continuously deformable to a loop! @bostonsymmetry @HLawrenceCS @mweber_PU @mathildepapillo
Sometimes the cure can be worse than the disease. Oversmoothing in GNNs is a big issue. Unitarity prevents all smoothing, fixing this. But for many dynamics problems, we want some smoothing! Relaxed unitary convolutions are the sweet spot.
I'll be @icmlconf presenting our work Smoothness Errors in Dynamics Models and How to Avoid Them, with Luisa Li, @park_jungy , and @RobinSFWalters !!
Come see our poster #2200 , july 9th, 2:30 PM – 4:15 PM, hall A.
Links to paper, website, and code in thread!
Robin Walters retweeted
I'll be @icmlconf presenting our work Smoothness Errors in Dynamics Models and How to Avoid Them, with Luisa Li, @park_jungy , and @RobinSFWalters !!
Come see our poster #2200 , july 9th, 2:30 PM – 4:15 PM, hall A.
Links to paper, website, and code in thread!
This work evolves our previous work LieGAN (arxiv.org/abs/2302.00236) which had some optimization issues, especially for discrete groups. LieGAN is great, but it stored only a point estimate of the symmetry generators at any given time.
(1/8) Happy to share that our paper LieFlow has been accepted to #ICML2026.
Symmetry is a strong inductive bias in ML, but you have to know the symmetry in advance. Can a model discover it directly from data, for both discrete and continuous groups? 🧵
Robin Walters retweeted
(1/8) Happy to share that our paper LieFlow has been accepted to #ICML2026.
Symmetry is a strong inductive bias in ML, but you have to know the symmetry in advance. Can a model discover it directly from data, for both discrete and continuous groups? 🧵
Robin Walters retweeted
5 more days (AOE) to submit to the 2026 TAG-DS collaborative conference organized in partnership with @bostonsymmetry! Don’t miss out on this awesome opportunity to share your work with this vibrant research community! Info at: tagds.com/events/tag-ds-2026
Robin Walters retweeted
Our community poster session starts in 30min and runs til 5:30pm, followed by a social nearby! The closest entrance to the Raytheon Amphitheater is here: maps.app.goo.gl/KvuYHVUYKi2L…
Robin Walters retweeted
@bostonsymmetry is hosting a poster session (4-5:30pm) + social on Tuesday, June 9th, at Northeastern! All are welcome to come chat about geometry, symmetries, + AI!
Location: Raytheon Amphitheater, maps.app.goo.gl/oDZc3Rw7iN4q…
Register here: neu.co1.qualtrics.com/jfe/fo…
Robin Walters retweeted
Just under two weeks until the submission deadline for the Boston TAG Party 2026– a joint conference organized collaboratively by the Boston Symmetry Group and TAG-DS! Papers are due June 12th— full archival papers, extended abstracts, and open problem tracks!
Robin Walters retweeted
Last Thursday, @stefanos_pert Stefanos Pertigkiozoglou defended his PhD. Stefanos is one of the deepest and most thorough thinkers I worked with. He is the definition of quiet power. His key insight was that enforcing exact equivariance throughout optimization can unnecessarily restrict expressivity. By relaxing equivariance constraints during training, his methods reached solutions that preserve the benefits of symmetry while escaping the restricted equivariant landscapes (ICML'25 and Neurips'24, plus TMLR, ICLR, Neureps). I am so proud of you Stefanos!
Thank you @_onionesque for the inspiration and Stefanos' mentoring in the relaxation work, as well as to @RobinSFWalters, @ParisPerdikaris, @EdgarDobriban, Pratik Chaudhari, and Jean Gallier, for making committee exams a resource for learning.
Robin Walters retweeted
Can BC policies be quickly improved through real world experience?
Our new #RSS2026 paper proposes Q2RL, a method that bridges BC and RL for on-robot learning.
Q2RL improves BC policies by up to 3.75x with just 1-2 hours of online interaction!
So when life gives you BC, make Q-functions! 🍋
Details in thread 🧵
Robin Walters retweeted
And now we are very proud and humbled to have received the ICLR 2026 Honorable Mention award for this work blog.iclr.cc/2026/04/23/anno… Very fun to have found this useful math nugget that can actually speed-up LLM training.
Robin Walters retweeted
TL;DR: poster today at 3:15pm, P3-#1109!
Have you ever benchmarked your method on QM9, MD17, OC20, or ModelNet? It turns out that the 3D orientations of point clouds in commonly used datasets are highly non-random. How did we prove this and why should you care? 🧵
Robin Walters retweeted
Introducing our recent work [ICLR2026] EquAct: An SE(3)-Equivariant Multi-Task Transformer for 3D Robotic Manipulation with Yu Qi, Yizhe Zhu, Robin Walters, and Robert Platt.
[Paper](openreview.net/forum?id=d1wu…）
[Video](youtu.be/ymrNQusB6Mw?si=D0mT…）
[Code](github.com/ZXP-S-works/EquAc…