A challenge for ML diagnosticians: The patient, Segment-Anything-Model-2 (SAM-2),... is presenting with two prominent symptoms: Symptom 1) Extremely high-magnitude tokens spread evenly across spatial dimensions.show more

🚨 Meta introduces Segment Anything Model 2 (SAM 2)... — the first unified model for real-time, promptable object segmentation in images & videos. 🚀SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences ➡️show more

Introducing segment-geospatial, A Python package for segmenting geospatial data... with the Segment Anything Model (SAM) GitHub: Docs: Notebook: #segmentanything #deeplearning #geopythonshow more

segment-geospatial v0.3.0 is out - segmenting satellite imagery with... the Segment Anything Model (SAM). GitHub: Docs: Notebook: #segmentanything #deeplearning #geopython #geospatialshow more

Today we're releasing the Segment Anything Model (SAM) —... a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️show more

Tree extraction from satellite imagery using segment-geospatial v0.5 and... the Segment Anything Model (SAM) - by Lucas Prado Osco LinkedIn post: Notebook: #geospatial #segmentanythingshow more

Your patient presents with the following symptoms. What is... your diagnosis? 💭show more

Apparently SeeDance 2 is down for the time being... on BytePlus but here's a young wizard with his dragon companion. It's a very cool video model. This video cost $0.72 USD to generate which seems reasonable. (300,000 tokens for a 15 secs at $0.0024 USD per 1000 tokens.)show more

Joey OaKKKKKKKKie! He fans a season-high 8 batters across... 3.2 IP for the Hill City Howlers 🔥 Final line: 3.2 IP, 2 H, 1 R/ER, 2 BB, 8 Kshow more

Two really good reasons to buy the Model Y... 1. It's fun to drive 2. FSD is the real dealshow more

Two videos of Russian interceptor drones with AI-targeting The... first is the 'Bolt' UAV, a new model with ~15km range The second is the Yolka, a very common model with 2-3km range. It has no explosives, only kinetic forcesshow more

1/ Today, Veo 2, our state-of-the-art video model, is... rolling out to Gemini Advanced + Whisk! You can create 8s, high-res videos from text prompts in Google Gemini with fluid character movement + lifelike scenes across a range of styles. Tip: the more detailed your description, the better.show more

T4 | Zags 2, Lopes 1 Sam Stem comes... through with the RBI double! 2-for-3 so far in his first career start. Wow.show more

The easiest cure for 2-High Safeties is a Fullback

🇺🇸 INSTA360 SPATIAL CAPTURE CHALLENGE is live! Ready to... relive the moments in 3D? Shoot with the Insta360 X5 or X6, create with Spatial Capture, and enter for a chance to win big with $3,500 in prizes! 🏆 PRIZES • Grand Prize ×1: $2,000 (Most-liked entry on the challenge voting page) • Creative Awards ×3: $500 Each • Monthly Winner: X6 Essentials Bundle + Insta360 Merch • Weekly Winner: Insta360 Merch HOW TO ENTER Step 1: Create your 3D model with X5 or X6, then get a share link from the Insta360 app Step 2: Submit your link through the form in our bio Step 3: Share on Instagram, tag Insta360 United States, and use #Insta360SpatialCapture for a bonus entry 📅 Submissions close DEC 20 Enter now via link in bio. #Insta360SpatialCapture #Insta360 #3DCapture #SpatialCapture #360Camerashow more

How to swap tokens across different chains with YOUR... Ronin Wallet Step 1: Open your Ronin Wallet Step 2: Click “Swap” Step 3: Choose the tokens you want to swap, select their respective chains, and input an amount!show more

Spags showing Tua 2-high to 1-high back to 2-high... This is the defensive equivalent to Reid’s ring-around-the-Rosie playshow more

Informative animation by Steven Bernard using ACLED data to... visualize the frequency, magnitude & spatial distribution of violent attacks across the Sahel for Aanu Adeoye's latest Big Read for the Financial Times on the ongoing jihadist insurgency:show more

6. Edit input video with text, here I reckon... we have SAM 2 working in combination with the new video model.show more

a Vietnamese AI engineer just built a real-time system... that counts objects moving down a conveyor belt. it runs on ultralytics' objectcounter. train a detector, define the region you care about, and it handles the rest. works for anything on a line, parts, packages, produce. the clever bit: instead of hand-labeling thousands of frames, he took a single frame, pre-annotated it with meta's segment anything (sam-2, built into ultralytics), and trained yolo11-nano on just that. one annotated frame, and it tracks objects accurately across the entire video.show more