I’ve launched 2 new course websites for my Introduction to #ComputerVision and #DeepLearning in Computer Vision courses. 🆕 Gaussian Splatting 🆕 Flow Matching 🆕 Sparse Autoencoders 🆕 Lecture Notes (work in progress) The videos don’t include voiceovers, but that’s coming in a future revision 🤞 Share your feedback in the thread.

arXiv has updated our policy on rate limiting for all submitters. This update was made to fairly distribute moderator time & support the arXiv community of staff, volunteers, readers & authors. Please read our announcement to learn more: blog.arxiv.org/2026/10/01/up…

Apple is going to make it even harder to productively use macOS in the age of agents? Bold move. Let's see how it plays out!

friday night in sf alcohol consumption : 0% token consumption: 100% (the urge to ask what he’s working on)

(1/8) We are excited to share our new model ARROW 🏹 ! ARROW brings D4RT-style decoding to broader input types, including multi-view videos and unordered collections of images. 📜arXiv: arxiv.org/abs/2610.01314 🌐Project page: vision.rwth-aachen.de/arrow

So true

Anniversary date night 🥂

Codex goal mode: “Don’t come back until it’s pixel-perfect.”

Live footage of a successful paper review rebuttal 😅

Take care of your parents, just as they took care of you. Be loving and present.

ChatGPT can now do motion design in After Effects. Introducing Higgsfield AI Motion Designer. Our ChatGPT plugin understands animation principles, writes expressions, and retains context in your After Effects projects. Try Higgsfield’s ChatGPT plugin now in After Effects.

… and we’re off! The #ICLR2027 review period has started.

Joshaghani et al., "What Builds the Scene? Luminance Dominates Geometry Formation in 3D Gaussian Splatting" This work reminded me of something that I completely forgot. We used to use grayscale images because that was all we needed to infer geometry and shapes. It still holds!

Feed-forward models distort geometry even when given camera poses. In paper to appear in #NeurIPS, we recast multi-view stereo as sequence-to-sequence: a camera-aware transformer with a unified global cost volume predicts geometry for all views jointly. arxiv.org/abs/2609.24850