Prof @NUSingapore #GraphNNs #LLMs #Theory #MolecularMaterialScience #Teacher #NRF_Fellow #MediocreImmigrant Opinions my own
Singapore
Joined March 2016
- Tweets1.5K
- Following893
- Followers17.7K
- Likes18.2K
Graph Machine Learning course
Lecture 10 presents GNNs Meet Large Language Models 🌟
Text-attributed graphs, open-weight LLM reasoning, LLM-to-LM interpreter, LoRA adapter, GraphRAG, graph soft-token, G-Retriever.
storage.googleapis.com/xavie…
Glad to be speaking tomorrow at the workshop on Structured Learning, organized by @smnlssn and his colleagues.
Happy to announce this years Structured Learning Workshop, Oct 27–28 at Chalmers, Gothenburg! Exceptional speakers from academia & industry. Limited spots, apply to attend via the waiting list: chalmers.ungapped.io/Events/…
Graph Machine Learning course
Lecture 9 presents Graph Transformer 🌟
Graph Laplacian/random walk encoding, over-squashing, sparse/dense graph self-attention, trilinear edge features, hierarchical GT, heavy-edge matching, O(n) hierarchical attention.
storage.googleapis.com/xavie…
🚀 Nobel Laureate Prof. Novoselov and I are hiring 2 postdocs to work on an NRF-funded project at the intersection of AI and materials science! Goal: Next-gen generative models for synthesizable materials. Strong background in DL or Physics/Chemistry? Send CV [email protected]
Graph Machine Learning course
Lecture 8 presents Graph Convolutional Networks 🌟
Convolution on grids/graphs, shared template matching, spectral convolution, Fourier transform, Chebyshev polynomials, an/isotropic aggregation, ChebNet, GCN, GAT, GatedGCN.
storage.googleapis.com/xavie…
After the Erdős number and the Kevin Bacon number, we now have the Yann LeCun number 😁
alphaxiv.org/number/@yann-le…
Six degrees of Yann LeCun
We mapped the coauthorship graph of every AI researcher on arXiv 🚀
Enter any two names to find the shortest path of papers connecting them
What’s your @ylecun number?
alphaXiv.org/number/@yann-le…
Graph Machine Learning course
Lecture 7 presents Shallow Graph Learning 🌟
Graphlets, Laplacian Eigenmaps, shortest paths, diffusion distances, Weisfeiler-Lehman graph isomorphism, DeepWalk/Node2vec, skip-gram, negative sampling.
storage.googleapis.com/xavie…
"When a measure becomes a target, it ceases to be a good measure."
Goodhart’s Law
Academia is long overdue for a change of how it evaluates researchers.
Prof Karikó 2023 Nobel is the example of the failure of # publications.
Time to emphasize quality/impact over quantity.
I will present tomorrow our recent work on Crys-JEPA, where we use Joint Embedding Predictive Architectures to learn crystal distributions for materials discovery.
linkedin.com/posts/zhongpc_a…
Excited to announce our @ipam_ucla long program on AI in Materials Science, Sep–Dec 2027 w/
@eigensteve @ChengBingqing S.Chmiela G.Csányi G.Dusson @ask1729 M.Meila K.Novoselov @ProfvLilienfeld
A great place to meet people across scientific boundaries!
ipam.ucla.edu/programs/long-…
What are the training datasets driving AI for materials science?
As I am updating my GraphML course, I prepared a series of slides introducing the datasets in the field, with short summaries and links to the papers and datasets.
Sharing them below:
dropbox.com/scl/fi/3vs04g2in…
It's been 10 years since we published Spectral Graph Convolutional Networks at @NeurIPSConf! 🎂
So much has happened since then, with the growth of the #GNN community.
It is dangerous to predict the future but GNNs+AI4Science feels just getting started :)
scholar.google.com/scholar?q…
How do we design materials with AI?
Excited to introduce Crys-JEPA, a new generative technique in collaboration w/ @liun_online, Kostya Novoselov, @ylecun & team. We achieved 47.9% VSUN on MP20 by building a high-quality energy-aware latent space with JEPA
arxiv.org/pdf/2605.14759
Michael @mmbronstein is the best possible host ! 🐴 😁
Awesome news! Huge congratulations to @ylecun and the entire team -- big things ahead!
Unveiling our new startup Advanced Machine Intelligence (AMI Labs).
We just completed our seed round: $1.03B / 890M€, one the largest seeds ever, probably the largest for a European company.
We're hiring!
[the background image is the Veil Nebula - a picture I took from my backyard, most appropriate for an unveiling]
More details here:
techcrunch.com/2026/03/09/ya…
Two great discussions on AI + Math/Science from last week at @ipam_ucla :
Fireside Chat with Terence Tao & Mark Chen: youtube.com/watch?v=ddTvK9nl…
Accelerating Math and Theoretical Physics with AI: youtube.com/watch?v=chMdygrf…
@KyleCranmer
On my way to IPAM/UCLA (back to my postdoc roots) -- Looking forward to teaching GenAI ! 🧑🏫
I will be teaching a two-day training course on deep learning at @ipam_ucla (UCLA) in March 5-6 2026 💻🌴🌅
If you want to understand diffusion models, transformers and LLMs from first principles, this training is for you !
ipam.ucla.edu/programs/speci…
