🔥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

✨ Top Reviewers of LoG 2024 ✨ Thank you to our incredible reviewers who went above and beyond to provide thoughtful and constructive feedback! 🙏 👏 Your efforts are the backbone of LoG’s success!

[1/N] 🚨 New Paper Alert 🚨 Context-Aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods 📜 arXiv-arxiv.org/abs/2410.17222 📘 Hugging Face Paper-huggingface.co/papers/2410.17… 🤖 HF PEFT Implementation-huggingface.co/docs/peft/main… 💻 Colab-colab.research.google.com/drive/1UhQDVhZ…

[5/N] Many thanks to my amazing co-authors! This work wouldn’t have been possible without your insights and dedication. Excited to see our efforts recognized at #WACV2025! 🎉 Roy Ganz , Chaim Baskin, Michael Elad, and @AlexBronstein—thank you!

🌟 Exciting PhD opportunity! 🎓 Join the innovative team at Ben Gurion University's Deep Learning Lab. Dive into groundbreaking research at the intersection of deep learning, generative models, and signal processing. Apply now ! 🚀

The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here: drive.google.com/file/d/1eLa3y2…

"Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning" by Haitz Sáez de Ocáriz Borde ,Artem Lukoianov , Anastasis Kratsios, Michael Bronstein,xiaowen dong Paper: arxiv.org/abs/2411.00835 #graphneuralnetworks

Linear Attention and Beyond: Interactive Tutorial with Songlin Yang (Songlin Yang MIT/Flash Linear Attention) I didn’t follow some of the recent results, so I zoomed Songlin and she explained it all to me for two hours 😂 youtu.be/d0HJvGSWw8A

Put simply: if you spend time on the Internet, you're very likely interacting with a GNN every day. Snapchat has officially joined the party! 📸

Gill Verdon Pinterest: arxiv.org/abs/1806.01973 Google Maps: arxiv.org/abs/2108.11482 Amazon: amazon.science/publications/p… Uber Eats: uber.com/en-GB/blog/ube… AirBnb: medium.com/airbnb-enginee… Alibaba: arxiv.org/abs/1902.08730 Spotify: arxiv.org/abs/2403.05185 LinkedIn: arxiv.org/abs/2402.11139

Quantization in the era of reasoning models: How does quantization impact the reasoning capabilities of DeepSeek-R1 models across distilled Llama and Qwen families? 👇 Check the thread for two surprising findings in evaluations of these models!

🎉📷#CVPR2025 [Rating: 5,5,5]. Glad to share that our paper, "Dataset Distillation with Neural Characteristic Function: A Minmax Perspective," has been accepted to CVPR 2025. Thanks! 1. Paper: raw.githubusercontent.com/gszfwsb/NCFM/r… (arxiv is coming soon!) 2. Code: github.com/gszfwsb/NCFM

Post-training of large language models through 7 years

AWESOME course 🚨 Check out this 🆕 MIT CSAIL lecture series with a unified presentation of Flow Matching and Diffusion Models I’ve been binge watching them 😎

pretty mind-blowing fact I just learned about transformer language models: the positional embeddings don't really do anything. you can just get rid of them and the model still works just as well sounds impossible, doesn't it? turns out standard LLMs aren't actually

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: jmlr.org/papers/v26/24-…

🚨Tutorial on Positional and Structural Graph Representations invariances.org/graph-represen… Given at the National Institute for Theory and Mathematics in Biology. Thanks to Claire Donnat and Olga Klopp for the invitation! Haggai Maron, the tutorial is finally out!

That's next year's GNN course motivating example sorted :)

Diffusion LLMs are the next big thing apparently

GLOW is coming back this Wednesday! 🌟 We will hear from – and interact with – Christian Koke (incorporating scale in GNNs) and Yonatan Sverdlov (sparse geometric MPNNs and their expressive power). 🗓️When May 28th, 5pm CEST on Zoom. 🌐 Details & sign-up: sites.google.com/view/graph-lea….

Welcome aboard Krishna Sri Ipsit Mantri 🎉🥳🎉🚀🏆