Sign in

Melanie Weber

@mweber.bsky.social
43 followers 9 following 11 posts

Assistant Professor @Harvard. Previously Hooke Research Fellow @Oxford and PhD @Princeton. Studying Geometry and Machine Learning.

PostsRepliesMedia
Melanie Weber @mweber.bsky.social · 02/03/2026
Can we reconstruct heterogeneous protein conformations from cryo-EM data while respecting molecular geometry? We present a geometry-aware framework that leverages graph-based representations and exhibits high reconstruction accuracy. arxiv.org/pdf/2602.21915
010
Melanie Weber @mweber.bsky.social · 15/01/2026
Can GNNs color graphs? We study GNN-based neural algorithmic reasoning for approximate k-coloring, introducing differentiable objectives and recursive warm starts that allow GNNs to outperform classical methods at scale. Led by Knut Vanderbush. Details here: arxiv.org/pdf/2601.05137
011
Melanie Weber @mweber.bsky.social · 03/12/2025
Check out our latest work on Geometric Machine Learning at #NeurIPS this week. We are also recruiting PhD students and postdocs — please reach out if you are interested in joining us. sites.harvard.edu/weber-group/...
sites.harvard.edu
[12/2025] Presentations from the Group at NeurIPS 2025
We are presenting several recent works at NeurIPS this year. Congratulations to all authors! Main conference: Higher-Order Learning with Graph Neural Networks via Hypergraph Encodings by Raphael Pelle...
010
Reposted by Melanie Weber
Kempner Institute at Harvard University @kempnerinstitute.bsky.social · 06/11/2025
Congratulations to #KempnerInstitute community members @msalbergo.bsky.social and @mweber.bsky.social — recipients of @schmidtsciences.bsky.social AI2050 Fellowships! 🎉 Discover their innovative research shaping the future of AI 👉 bit.ly/47Do4R3 #AI
bit.ly
Schmidt Sciences Awards Early Career Fellowships to Michael Albergo, Melanie Weber - Kempner Institute
Two Kempner Institute community members have received AI2050 Fellowships from Schmidt Sciences, a nonprofit organization aimed at accelerating scientific knowledge and breakthroughs. The AI2050 Progra...
0134
Melanie Weber @mweber.bsky.social · 03/11/2025
How can we reliably optimize on manifolds learned from data? We present an iso-Riemannian optimization framework that overcomes challenges of classical methods, and allows for interpretable clustering and efficient inverse problem solving, even in high dimensions. Lead:@WillemDiepev1. bit.ly/4hG5Seh
020
Melanie Weber @mweber.bsky.social · 17/10/2025
How does neural feature geometry evolve during training? Modeling feature spaces as geometric graphs, we show that nonlinear activations drive transformations resembling Ricci flow, revealing how class structure emerges and suggesting geometry-informed training principles. arxiv.org/abs/2509.22362
010
Melanie Weber @mweber.bsky.social · 05/09/2025
Convexity verification is central to optimization in ML and data science. We introduce a framework for testing geodesic convexity in nonlinear programs on geometric domains. Julia implementation available to leverage certificates in applications. Led by Andrew Cheng, Vaibhav Dixit. bit.ly/3HIlkJu
040
Melanie Weber @mweber.bsky.social · 28/08/2025
Single-cell data reveals developmental hierarchies, but common embeddings distort them. We present Contrastive Poincaré Maps, a self-supervised hyperbolic encoder that preserves hierarchies, scales efficiently, and uncovers lineage across datasets. Lead: @nithyabhasker.bsky.social 🧬 bit.ly/4211hMY
000
Melanie Weber @mweber.bsky.social · 22/08/2025
🚀 CALL FOR SUBMISSIONS: Non-Euclidean Foundation Models & Geometric Learning Workshop @ NeurIPS 2025 🚀 ⏰ DEADLINE: Sep 2, 2025 📥 SUBMIT HERE: bit.ly/3UDTvEX Join our reviewer pool: bit.ly/3JvvI7K 🔗 Full details: bit.ly/41PDyiM
bit.ly
NeurIPS 2025 Workshop NEGEL
Welcome to the OpenReview homepage for NeurIPS 2025 Workshop NEGEL
071
Reposted by Melanie Weber
Kempner Institute at Harvard University @kempnerinstitute.bsky.social · 25/04/2025
4/26 at 3pm: 'Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups' Zakhar Shumaylov · Peter Zaika · James Rowbottom · Ferdia Sherry · @mweber.bsky.social · Carola-Bibiane Schönlieb Submission: openreview.net/forum?id=7PL...
111
Melanie Weber @mweber.bsky.social · 16/04/2025
Community detection is a classical graph learning task. Our new JMLR paper shows how discrete Ricci curvature and geometric flows unveil (mixed) communities and studies relations between the curvature of a graph and its dual. w\ Yu Tian, Zach Lubberts: www.jmlr.org/papers/v26/2...
010
Melanie Weber @mweber.bsky.social · 08/04/2025
A postdoc position is available in my group at @harvard.edu Applied Math to perform research in Riemannian Optimization. More details, including on how to apply, can be found here: academicpositions.harvard.edu/postings/14832
academicpositions.harvard.edu
Postdoctoral Fellow in Riemannian Optimization
A postdoctoral position is available in the Geometric Machine Learning Group at Harvard University, led by Prof. Melanie Weber. This role offers an opportunity to perform research on Riemannian Optimi...
000
Reposted by Melanie Weber
Nina Miolane @ninamiolane.bsky.social · 25/02/2025
Want to learn more?🧐 📺 Subscribe to the NeurReps YouTube channel and find more talks by @mweber.bsky.social @kostaspenn.bsky.social @robinwalters.bsky.social @erikjbekkers.bsky.social S. Ravanbakhsh @andyrepair.bsky.social & more! youtube.com/@neurreps
youtube.com
NeurReps
Official YouTube channel of the Symmetry and Geometry in Neural Representations (NeurReps) workshop.
175
Melanie Weber @mweber.bsky.social · 21/02/2025
Hypergraphs naturally parametrize higher-order relations.Yet GNNs on hypergraph expansions often outperform specialized topological models. We show that adding hypergraph-level encodings yields significant performance and expressivity gains.w/ Raphael Pellegrin, Lukas Fesser arxiv.org/pdf/2502.09570
062