🔥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

Optimization researchers of the world, unite!

#NeurIPS2023 reviewer bidding question: What is the relative position of a paper without any bid? Is it: 1. Same as "Neutral" 2. Lower than "very low" 3. Other (?) NeurIPS Conference

We live in the differentiable programming era. No one implements backward procedures anymore (or so I hope) and this "trick" should have been too obvious by now. Yet, I see that almost any intro course to DL spends a significant time explaining this

NeurIPS discussion period is fun #NeurIPS2023 #NeurIPS

When you discover the implicit bias of a machine learning algorithm. Every time.

DecoReco accepted at #NeurIPS2023! 🥳 See you in NOLA 🎷

Fascinating talk by Gael Varoquaux 🦋, (Godfather of scikit-learn 😅) on model evaluation. Closed some knowledge gaps I felt I had, especially in evaluating models on imbalanced data

Idempotent Generative Network project page: assafshocher.github.io/IGN/ abs: arxiv.org/abs/2311.01462 Introduces a new generative modeling framework that utilizes three objectives: a reconstruction loss, an idempotent objective, and a tightness objective. The key idea is that for

On my way to #NeurIPS2023. Excited to catch up with old friends and meet new ones. DM or meet us at our poster on Thursday.

📣 We are looking for a PhD intern interested to work with us on generative models in FAIR EMEA (specifically, Paris)!

We're organizing the 1st workshop on Prompting in Vision at #CVPR2024 in Seattle. We have an amazing line of speakers, and we accept 8-pages paper submissions. Stay tuned! Website: prompting-in-vision.github.io/index_cvpr24.h… OpenReview: openreview.net/group?id=thecv…

Q: You sample random neural networks until you find one with perfect training accuracy. What will be the generalization error? A: Typically good — We prove that when a “simple explanation” exists, such sampled NNs (MLP/CNNs) generalize well! arxiv.org/abs/2402.06323

Ever wondered how humans would perceive the world with eyes 1000x faster, sensitive to infrared, or capable of "seeing" coffee cup vibrations from our voice? For humans, it's a mystery. But for 𝗺𝗮𝗰𝗵𝗶𝗻𝗲𝘀, my group at WIS aims to answer these ques., and you can take part!

🎓 I will be giving a guest lecture in the upcoming Generative Modeling Summer School at TU Eindhoven Jakub Tomczak, thank you for the invitation!

My two cents on the 'who has the biggest "science"?' debate is: check out this incredible CrashCourse playlist: youtu.be/YvtCLceNf30?si…