Hannah Lawrence

@HLawrenceCS

Former PhD @ MIT CSAIL. Finding/exploiting patterns in data, especially symmetries. AI4Science. hannahlawrence.github.io. Cofounder @bostonsymmetry.

Joined April 2021

783 Following

973 Followers

Replies Reposts Media

Pinned
Hannah Lawrence
@HLawrenceCS
Jun 3
@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/oDZc3Rw7iN4qTU… Register here: neu.co1.qualtrics.com/jfe/form/SV_77…
Hannah Lawrence
@HLawrenceCS
Apr 25
Was the whole blogpost an excuse to make this meme? Perhaps.
Julia Balla
@julballa
Apr 25
Replying to @julballa
We must choose both the tokens AND their order. A joint distribution can be factored into a product of conditionals in any order, but this choice determines the available context at each step. Thus, some orders are easier to model in practice (arxiv.org/abs/2502.06768) (2/7)
GIF
Hannah Lawrence
@HLawrenceCS
Apr 25
Come chat about tokenization and trends in the treatment of non-sequential data! P4-5313
Julia Balla
@julballa
Apr 25
New blogpost on tokenizing non-sequential data! Language has sequential structure, which gave rise to the next-token prediction paradigm of LLMs. But we increasingly use LLMs for data without inherent order (e.g. images, molecules, sets). What does “next token” mean here? (1/7)
Hannah Lawrence
@HLawrenceCS
Apr 23
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? 🧵
1
Hannah Lawrence
@HLawrenceCS
Apr 23
Will be presenting this work on Saturday at 3:15pm local time (on behalf of all my co-authors)! Come chat about generalizing positional encodings for selectively breaking model invariances :)
Teresa Huang
@TeresaNHuang
Apr 23
Excited to share that ASEN, our framework towards equivariant foundation models, is accepted to #ICLR2026! 📜paper: arxiv.org/abs/2603.19486 📍poster: Sat 4/25 PM, P3-#726 w/ Abhinav Goel, @dereklim_lzh, @HLawrenceCS, Stefanie Jegelka

Hannah Lawrence

Hannah Lawrence’s posts