🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Regardless of what you do and what you achieve, people always have something to say (including me). Ignore the noise. #NobelPrizePhysics

My research journal saved me today. Highly recommend fellow grad students to log in a journal everyday.

My paper "Rethinking Fine-tuning Through Geometric Perspective has been accepted" to UniReps workshop of NeurIPS Conference ! openreview.net/forum?id=FFQ5T…

!apt install texlive-fonts-recommended texlive-fonts-extra cm-super dvipng import matplotlib.pylab as plt plt.rcParams.update({ "text.usetex": True, "font.family": "serif", "text.latex.preamble": "\\usepackage{amsmath}"})

import ssl ssl._create_default_https_context = ssl._create_unverified_context

It’s that time of the year again

Browsing PASCAL dataset to cheerypick predictions is fun. Lots of meme-worthy images. #CVPR2025 #CVPR2025

Entered my buzz cut era. 🙄

This app’s icon is similar to \mathbb{X}

Graph structure typically influences only node embeddings in GNNs. What if activation functions were graph-adaptive too? Introducing DiGRAF: a novel activation function for GNNs powered by learnable diffeomorphisms. Discover more at our poster #33 tomorrow at Learning on Graphs Conference 2024 🧠📈

If you are at #NeurIPS2024, don’t miss Moshe Eliasof presenting our 𝐆𝐑𝐀𝐍𝐎𝐋𝐀: 𝐀𝐝𝐚𝐩𝐭𝐢𝐯𝐞 𝐍𝐨𝐫𝐦𝐚𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧 𝐟𝐨𝐫 𝐆𝐫𝐚𝐩𝐡 𝐍𝐞𝐮𝐫𝐚𝐥 𝐍𝐞𝐭𝐰𝐨𝐫𝐤𝐬! 📅 Today 11 am 📍 East Exhibit #3000 Joint work w/ Carola-Bibiane Schönlieb Haggai Maron

Thrilled to present DiGRAF at NeurIPS Conference with Bruno Ribeiro and Moshe Eliasof. Big thanks to everyone who stopped by, asked questions, and offered feedback. DM to grab a coffee and discuss ideas. We’re excited about the directions this work will take—stay tuned for more to come!

Slides of my presentation "Mathematical Foundations of Graph Foundation Models" yesterday at the AMS Session of the #JMM2025. The accompanying paper is coming soon. cs.purdue.edu/homes/ribeirob…

This is the sign I needed today! 🤡

🚨 New paper at #ICLR2025! 🧵Introducing Holographic Node Representations, pretrained general-purpose node embeddings that adapt to any graph task (node, link, high-order) 📍Fri 10 AM SGT Hall 3 + 2B #189 presented by Josh Robinson w/ Josh Robinson Jure Leskovec Bruno Ribeiro 1/8

Excited to announce I’m joining INSIGHT Lab w/ Chaim Baskin at BGU’s School of ECE this summer! I’ll be working on ODE-inspired methods to advance representation learning! Huge thanks to Prof. Baskin for making this possible!