1/5 Last week, we released an updated version of... CoTracker, our transformer-based model for tracking any point in a video. It’s now capable of tracking 10x more points than before!show more

We're very excited to introduce TAPNext: a model that... sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: 🧵show more

Can we robustly track an object’s 6D pose in... contact-rich, occluded scenarios? Yes! Our solution, V-HOP, fuses vision and touch through a visuo-haptic transformer for precise, real-time tracking. arXiv: Project:show more

Last week we released our Gemini 3.1 Pro Deep... Think model. Here are a succession of examples of that model doing heat transfer analysis. No tools, just Deep Think and Image Generation. Step 1: generate a CAD file from a technical drawing.show more

This is how you unlock the next billion software... developers. The new Replit ⠕ Agent 3 (they just launched) is the most advanced vibe-coding agent in the world. 1. Smarter than any other vibe-coding model (10x more autonomous than the previous version). 2. It thinks harder and lasts longer than any other model (up to 200 minutes running fully autonomously). 3. The agent can now use an actual browser to test and fix its own code. 4. 3x faster and 10x more cost-effective than any other "Computer Use" for testing. 5. It can build other agents and automations to take care of repetitive tasks. Seeing the agent test the application autonomously is science fiction!show more

Our best look yet at the Mega Man motion... capture model in action from The Great Capcom Exhibition. It’s an updated version of the Mega Man 11 model, featuring adjusted proportions and subtle new details.show more

Excited to share our (w/ Vishakh Sandwar) entry to... the '25 #BigDataBowl! We built a Transformer-based model predicting man/zone coverage in the presnap... peaking at 89% accuracy before the snap— and 93% 1sec after the snap (More below!)show more

An update on the ancient art of tracking. Louis... Liebenberg is releasing CyberTracker Online, an app based on his 1998 Rolex Award-winning software that uploads real-time data. A new opportunity for managing vulnerable species. More #PerpetualPlanetshow more

SURPRISE! We have one more single for you before... the album is released. ”An Ocean Of Strange Islands” will be out on September 10th! Subscribe to our newsletter now to receive a snippet of the song, tomorrow!show more

Successful start to the week with the first skate... tagged in Courtmacsherry. Over the next 2 yrs we will be tracking its movements to identify residency within one of the last known refuges for this species in Ireland 🌊show more

THE SOUND OF SILENCE (LIVE) 🖤 OUT NOW Tomorrow... marks SIX YEARS since we released our version of #TheSoundOfSilence! To celebrate its anniversary, we JUST UPLOADED a NEW LIVE VIDEO performing the song. Watch now on our YouTube channel!show more

Ladybug’s Journey Part3, Fever Time 🎆 It’s time to... boost your Leaf Points 🍃 Play our new game GIGACHADBAT for more Leaf Points 🍃 Pack your Buggy Bag with various achievements made during the Ladybug’s Journey for a Leaf Point 🍃 boost of up to 10X and some hidden boost effects! Remember, The ladybug always goes up 🐞show more

Announcing the Immersive Web SDK (IWSDK)! Now developers can... leverage the capabilities of the Meta Quest, all from a browser-based experience. 👐 Hand Tracking & Controller Support 😎 Support for mixed reality passthrough 🔊 Spatial Audio 🧑‍💻 Built on top of Three.js A ton more:show more

We’re releasing model weights for our 8B- parameter Dynamic... Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.show more

GOOGLE 🔥: An upcoming Gemini Omni video model from... Google is expected to be much more advanced in video editing, capable of completing tasks like removing watermarks, replacing objects in the video, and more. It is also likely that Google will release 2 versions of this model, including a Pro variant. And I assume what we see isn't Pro? Anime sample 👀show more

Look at this crazy lightning! Shoutout to Luke for... sending this in from Lenexa, Johnson County, KS. We are tracking all of this severe weather right now. Tune into the live stream to see more.show more

Today, we are adding Stable Video Diffusion, our foundation... model for generative video to the Stability AI Developer Platform API. The model can generate 2 seconds of video, comprising of 25 generated frames and 24 frames of FILM interpolation, within an average time of 41 seconds. Developers interested in utilizing Stable Video Diffusion through an API can access it now on the Stability AI Developer Platform. Learn more here:show more

American Farmer - “Something ain’t right A the amount... of Alumina in our soil is now 5x 10x higher than it was this time last year” Farmers know because they analyse the soil - just another shocking consequence of “we spray a lot” comment Trump just made.show more

Taking in the blue skies and clear waters we... enjoyed for most of June before the weather broke last week - hopefully we'll be seeing more of it before long 🤞 County Clare, Ireland.show more

First normal portion of food I’ve seen her eat,... but then it’s smothered in a mayo-based dressing. I mean, it’s better than an entire chocolate cake. “Too light for me,” girl, we know 😭show more