I am delighted to announce that the camera-ready version of my new book, "Machine Learning: Advanced Topics", is finally available online for free at probml.github.io/book2 (The MIT Press @mitpress.bsky.social will publish the hard copy in 2023.)

Excited to share our ECCV oral! neuroailab.github.io/eisen/ "Unsupervised Segmentation in Real-World Images via Spelke Object Inference" A case of psych + neuroscience helping us build much better AI! Honglin Chen Rahul Venkatesh @_yonifriedman Jiajun Wu Josh Tenenbaum Daniel Yamins

The voice of reason, finally... The #iclr2023 ethics committee responded.

What are the best ways to make self-supervised visual representation learning more efficient? At #NeurIPS2022 tomorrow, we’re presenting new research showing how to evaluate the compute efficiency of popular pre-training methods. dpmd.ai/3i3Nr8y

Meanwhile me asking: "so where are we then?" SoTA VQA model: "at the gym"

Today we release LLaMA, 4 foundation models ranging from 7B to 65B parameters. LLaMA-13B outperforms OPT and GPT-3 175B on most benchmarks. LLaMA-65B is competitive with Chinchilla 70B and PaLM 540B. The weights for all models are open and available at research.facebook.com/publications/l… 1/n

OMG YES!! please do it. I’ve been frustrated with AMD software being so bad and missing out on DL ever since I started, which is over a decade ago. Because their hardware is/was dope. Seriously considered gambling my phd on doing this myself, though ended up deciding against.

Want to make sense of large embeddings? WizMap it!📍 WizMap is an interactive visualization tool for exploring embeddings. Seamlessly navigate through millions of points, while gaining valuable insights from multi-resolution summaries!! 👉 Try it now: poloclub.github.io/wizmap/

Mahesh Sathiamoorthy Someone has already expressed they were sad. Closed as duplicate.

Join us at the #CVPR2026 workshop on 'What is Next in Video Understanding?' to hear from our excellent line-up of keynote speakers. We also have an open call for 1-2 page position papers on the future of video understanding. winvu.github.io/cvpr-24/ #CVPR2024

Oh no😱

Some heartfelt sentiments here...

dr. jack morris It was adobe illustrator

Co-authors are all you need

this makes me so happy 🥳

1/2) Happy to share the preprint of our workshop paper on using information theory to find class separation in diffusion models It generalizes previous models of speciation and symmetry breaking to generic class definitions

🚀New from Meta FAIR: today we’re introducing Seamless Interaction, a research project dedicated to modeling interpersonal dynamics. The project features a family of audiovisual behavioral models, developed in collaboration with Meta’s Codec Avatars lab + Core AI lab, that

🚀Announcing C-RADIOv4: The latest evolution in our agglomerative vision backbone family is here! We’ve built a unified student model that distills the best capabilities of multiple state-of-the-art teachers into a single, efficient architecture. DINOv3, SAM3 and SigLIP2 all

🚀 New paper: arxiv.org/abs/2602.13191 VideoLMs are bottlenecked by a simple problem: they treat video like a stack of images. That means huge token costs, slow responses, and missed temporal details. What if we processed video the way codecs do? 🎬 Instead of dense

Giveaway time! Here’s your chance to win the Osmo Action 6 Standard Combo. How to enter: 1. Follow DJI 2. Like and share this post 3. Bonus Chance: Comment below what you’ll be filming with this camera in 2026. · Time period: 2026/3/6 - 2026/3/31.