Twitter Beğeni Hilesi

Pleased to announce we are releasing checkpoints for our SigLIP models! These are very strong image-text ViTs. We release them along with a colab to play around with. Most are english, but we also release a good i18n one. Sorry, no magnet link mic drop. More in thread🧶

Ever wondered if CLIP’s stellar generalization performance is just due to high train-test similarity, given its vast and diverse training data? In our new pre-print, we find CLIP seems to genuinely discover much more generalizable features! 1/8 arxiv.org/abs/2310.09562

v2.23.0 of OpenCLIP was pushed out the door! Biggest update in a while, focused on supporting SigLIP and CLIPA-v2 models and weights. Thanks Gabriel Ilharco giovanni Romain Beaumont for help on the release, and Santiago Castro for catching issues. There's a leaderboard csv now!

🚀Big updates to OpenCLIP! We now support over 100 pretrained models, and many other goodies. Check it out! github.com/mlfoundations/…

DINOv2+registers=♥️ We are releasing code and checkpoints for DINOv2 augmented with registers and a slightly better training recipe. No more of those pesky artifacts! Simple one-liner, try it out: dinov2_vitg14_reg = torch.hub.load('facebookresearch/dinov2', 'dinov2_vitg14_reg')

Trying to get into the Hugging Face party.. but if you’re not a Llama you’re not gonna make it ☹️

We've integrated a quantized CLIP model into our GitHub library for more efficient semantic image search. 🚀Now use your CPU to create low cost vector databases! Minor accuracy drop, but 2-3x speed boost on Intel CPUs with VNNI. Check it out! (1/4)💻✨LAION Neural Magic

Ten months ago, we launched the Vesuvius Challenge to solve the ancient problem of the Herculaneum Papyri, a library of scrolls that were flash-fried by the eruption of Mount Vesuvius in 79 AD. Today we are overjoyed to announce that our crazy project has succeeded. After 2000

Preprint "A call for embodied AI" with my coathors Giuseppe Paolo and Jonas Gonzales-Billandon. arxiv.org/abs/2402.03824

✨ ALL open weights T2I base models to date ✨ DALL-E Mini, Mega ruDALLE Latent Diffusion Stable Diffusion 1, 2, XL, Turbo Karlo IF Würstchen v1, v2, v3 (Stable Cascade) Kandinsky 2.1, 2.2, 3 PixArt-Alpha, LCM Segmind SSD, Vega, MoE Playground v2 huggingface.co/collections/mu…

Happy to announce our theoretical work on understanding compositional generalization for object-centric representations has been accepted as an oral at #ICLR2024! 📄 arxiv.org/abs/2310.05327 💻 github.com/brendel-group/… 1/11

Why do Random Forests perform so well off-the-shelf & appear essentially immune to overfitting?!? I’ve found the text-book answer “it’s just variance reduction 🤷🏼‍♀️” to be a bit too unspecific, so in our new pre-print arxiv.org/abs/2402.01502, Alan Jeffares & I investigate..🕵🏼‍♀️ 1/n

Part 2: So why DO Random Forests work?! On this, I’ll have to disagree with Elements of Statistical Learning (my first time ever 💔) EoSL says the success of forests should be understood as a consequence of variance reduction *alone*, but I think that’s not a good intuition 1/n

For those of you who were wondering what I’ve been doing since I joined Meta Reality Labs late 2022. Here is the first detailed scientific communication about our work. You can read the paper at: biorxiv.org/content/10.110…

Beluga whales love to play, scare, joke and generally interact with humans. This compilation is a good example. [📹 aquariumadvicesa]

"fly through tour of a museum with many paintings and sculptures and beautiful works of art in all styles" Video generated by #Sora

Ever feel frustrated when you vaguely know what paper you want to cite but can't find it on Google? Can LM-based agents automatically find paper citations for you? Our new paper presents a tough new benchmark for this task along with an LM-based agent for finding citations.

Introducing PaperQA2, the first AI agent that conducts entire scientific literature reviews on its own. PaperQA2 is also the first agent to beat PhD and Postdoc-level biology researchers on multiple literature research tasks, as measured both by accuracy on objective benchmarks