🔥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

I just pushed a new paper to arXiv. I realized that a lot of my previous work on robust losses and nerf-y things was dancing around something simpler: a slight tweak to the classic Box-Cox power transform that makes it much more useful and stable. It's this f(x, λ) here:

This is a quite nice set of notes from MIT on matrix calculus ideas that are commonly useful in machine learning. 1/2

Python library for creating math animations

“Mathematical rigor is like clothing: in its style it ought to suit the occasion, and it diminishes comfort and restricts freedom of movement if it is either too loose or too tight" -G.F. Simmons Tools that help us guess approximate answers are often very valuable. 1/2

Let's interact with the light waves! Here, I created a real-time simulation that can run in your browser: chiuhans111.github.io/interactwave/ You can change the beam width and the focusing power of the input light rays. Please give it a try and let me know your thoughts! #Optics #WebGL

I just wrote my first blog post in four years! It is called "Deriving Muon". It covers the theory that led to Muon and how, for me, Muon is a meaningful example of theory leading practice in deep learning (1/11)

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

Extracting structure that’s implicitly learned by video foundation models _without_ relying on labeled data is a fundamental challenge. What’s a better place to start than extracting motion? Temporal correspondence is a key building block of perception. Check out our paper!

🎉 Thrilled to share our CVPR 2025 Award Candidate & Oral paper: 🔹 GlobustVP Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World 🚀 A globally optimal & outlier-robust method for vanishing point (VP) estimation 🧱 Global optimality 💥 Tolerates up to

A post #ICCV2025 Slack message to my group. Hope others find it useful.

Angjoo Kanazawa Angjoo Kanazawa and I taught CS 280, graduate computer vision, this semester at UC Berkeley. We found a combination of classical and modern CV material that worked well, and are happy to share our lecture material from the class. cs280-berkeley.github.io Enjoy!

No