Loading video...

Video Failed to Load

Go Home

Apple’s Embedding Atlas (MIT license) lets you explore, cluster, search, and filter millions of points in real time with WebGPU. Great for AI, data science, and research. Demo: apple.github .io/embedding-atlas Source: github .com/apple/embedding-atlas

LeonWohlgemuth's profile picture

Leon

7,835 subscribers

30,860 views • 10 months ago •via X (Twitter)

Science & TechnologyNews & PoliticsEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Gemini Embedding 2 is now generally available in the Gemini API and Vertex AI! Start building with our first natively multimodal embedding model, now equipped with the stability and optimizations required for production apps.
0:13

Gemini Embedding 2 is now generally available in the Gemini API and Vertex AI! Start building with our first natively multimodal embedding model, now equipped with the stability and optimizations required for production apps.

Google AI Developers

813,782 views • 2 months ago

A little preview of embedding my polynomial roots #mathart into 3D. Made with #python #apple #MLX and #pyGFX
0:10

A little preview of embedding my polynomial roots #mathart into 3D. Made with #python #apple #MLX and #pyGFX

Simone Conradi

12,985 views • 1 year ago

3D embedding of my polynomial roots #mathart. Made with #python #apple #MLX and #pyGFX. Original 2d version below 👇
0:10

3D embedding of my polynomial roots #mathart. Made with #python #apple #MLX and #pyGFX. Original 2d version below 👇

Simone Conradi

10,903 views • 1 year ago

🆕 You can now pay for your Atlas incorporation and registered agent fees with USDC.
0:17

🆕 You can now pay for your Atlas incorporation and registered agent fees with USDC.

Stripe Atlas

102,227 views • 5 months ago

Oldies but goldies: M. Belkin, P. Niyogi, Laplacian Eigenmaps for Dimensionality Reduction and Data Representation, 2003. Non-linear dimensionality reduction by embedding data points using the eigenvectors of a graph Laplacian as coordinates.
0:10

Oldies but goldies: M. Belkin, P. Niyogi, Laplacian Eigenmaps for Dimensionality Reduction and Data Representation, 2003. Non-linear dimensionality reduction by embedding data points using the eigenvectors of a graph Laplacian as coordinates.

Gabriel Peyré

35,174 views • 2 years ago

Laplacian eigenmaps perform non-linear dimensionality reduction ("manifold learning") by embedding data points using the eigenvectors of a graph Laplacian as coordinates.
0:10

Laplacian eigenmaps perform non-linear dimensionality reduction ("manifold learning") by embedding data points using the eigenvectors of a graph Laplacian as coordinates.

Gabriel Peyré

67,757 views • 2 years ago

Listen to Nothin' and Atlas on Apple Music!
0:15

Listen to Nothin' and Atlas on Apple Music!

Guns N' Roses

41,823 views • 6 months ago

🚨 INSIGHT: Stagnant crypto engagement and lack of real-world connection are limiting blockchain adoption. Web3 is revolutionizing engagement by merging virtual and real-world experiences through tokenization, AI, and blockchain. Chain Atlas by Belong gamifies real-world exploration with geo-based NFTs and AI-guided missions to bring blockchain to life in cities worldwide. Chain Atlas lets players unlock NFTs and earn Proof-of-Location tokens by visiting landmarks, join blockchain clans, and compete for rewards, all within a $1M prize pool. Ready to explore your city and unlock blockchain rewards? [Cointelegraph Acceleration]
0:10

🚨 INSIGHT: Stagnant crypto engagement and lack of real-world connection are limiting blockchain adoption. Web3 is revolutionizing engagement by merging virtual and real-world experiences through tokenization, AI, and blockchain. Chain Atlas by Belong gamifies real-world exploration with geo-based NFTs and AI-guided missions to bring blockchain to life in cities worldwide. Chain Atlas lets players unlock NFTs and earn Proof-of-Location tokens by visiting landmarks, join blockchain clans, and compete for rewards, all within a $1M prize pool. Ready to explore your city and unlock blockchain rewards? [Cointelegraph Acceleration]

Cointelegraph

34,425 views • 1 year ago

Glimpse of real and simulated Atlas during Jensen's GTC keynote.
0:11

Glimpse of real and simulated Atlas during Jensen's GTC keynote.

The Humanoid Hub

254,110 views • 1 year ago

Outside time with Atlas
0:11

Outside time with Atlas

Crocodile Cam⚡️🇨🇻

42,259 views • 1 year ago

1 billion cells. One atlas. Today, Illumina introduces the Billion Cell Atlas, creating the most comprehensive map of human disease biology — and unlocking unparalleled speed and scale in AI for drug discovery. The Atlas will help researchers, including founding participants AstraZeneca, Merck, and Eli Lilly and Company study the effect of switching on and off all 20,000 genes in cells linked to diseases that have been historically difficult to decode. Learn how the Atlas will elucidate the biological pathways behind some of the world’s most devastating diseases: #JPM2026
0:12

1 billion cells. One atlas. Today, Illumina introduces the Billion Cell Atlas, creating the most comprehensive map of human disease biology — and unlocking unparalleled speed and scale in AI for drug discovery. The Atlas will help researchers, including founding participants AstraZeneca, Merck, and Eli Lilly and Company study the effect of switching on and off all 20,000 genes in cells linked to diseases that have been historically difficult to decode. Learn how the Atlas will elucidate the biological pathways behind some of the world’s most devastating diseases: #JPM2026

Illumina

34,129 views • 5 months ago

We’ve seen hydraulic Atlas backflip, and now electric Atlas can pull it off as well.
0:17

We’ve seen hydraulic Atlas backflip, and now electric Atlas can pull it off as well.

The Humanoid Hub

316,844 views • 1 year ago

Semantic search improves our agent's accuracy across all frontier models, especially in large codebases where grep alone falls short. Learn more about our results and how we trained an embedding model for retrieving code.
0:12

Semantic search improves our agent's accuracy across all frontier models, especially in large codebases where grep alone falls short. Learn more about our results and how we trained an embedding model for retrieving code.

Cursor

881,522 views • 8 months ago

🚨 3I/ATLAS: 5 OBJECTS! New Images captured by Rays Astrophotography showing the coma has 5 physical structures around 3I/Atlas. I had previously mentioned this to you all with data and proof.. Well look here we see it AGAIN! #3IATLAS #3IATLASExposed #UFOX #SPACE
0:12

🚨 3I/ATLAS: 5 OBJECTS! New Images captured by Rays Astrophotography showing the coma has 5 physical structures around 3I/Atlas. I had previously mentioned this to you all with data and proof.. Well look here we see it AGAIN! #3IATLAS #3IATLASExposed #UFOX #SPACE

Backseat Passenger 𒅒

126,702 views • 6 months ago

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung
1:51

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Pascale Fung

90,144 views • 6 months ago

พร้อมยัง ALIS❗️ ได้เวลาลุ้นวัตถุดิบปริศนาของ ATLAS มาดูกันว่า ATLAS จะเจออะไรในคนอร์ Mystery Box จะทำให้ ATLAS ยิ้มหวาน 😊 หรือเหวอ 😲 บอกเลยว่าห้ามพลาด! 💚📦✨ #วันนี้แอดไรใส่คนอร์โจ๊ก #คนอร์โจ๊กจัดเต็มคัพ #Atlasแอดไรใส่คนอร์โจ๊ก
0:15

พร้อมยัง ALIS❗️ ได้เวลาลุ้นวัตถุดิบปริศนาของ ATLAS มาดูกันว่า ATLAS จะเจออะไรในคนอร์ Mystery Box จะทำให้ ATLAS ยิ้มหวาน 😊 หรือเหวอ 😲 บอกเลยว่าห้ามพลาด! 💚📦✨ #วันนี้แอดไรใส่คนอร์โจ๊ก #คนอร์โจ๊กจัดเต็มคัพ #Atlasแอดไรใส่คนอร์โจ๊ก

KnorrThailand

37,597 views • 5 months ago

A NEW ATLAS AND THE STARS CLIP IS OUT! And it looks like Atlas and Atmosphere have found a new friend 🥺 #AtlasandtheStars #IndieAnimation
0:12

A NEW ATLAS AND THE STARS CLIP IS OUT! And it looks like Atlas and Atmosphere have found a new friend 🥺 #AtlasandtheStars #IndieAnimation

Mirandamations

21,584 views • 10 months ago

ATLAS ดูพร้อมแฟน ๆ ทุกคนครับ *พวกเราถ่าย reaction กันไปแล้วนะครับ แต่ก็ยังตื่นเต้นเหมือนเดิม* ATLAS - รักกันวันเดียว ( ONE DAY ) | Prod. by URBOYTJ 🔗 #วันนี้ATLASบอกรักกันวันเดียว #ATLASรักกันวันเดียว #AtlasNextJourney #ATLAS_th #ATLASth #URBOYTJ
0:17

ATLAS ดูพร้อมแฟน ๆ ทุกคนครับ *พวกเราถ่าย reaction กันไปแล้วนะครับ แต่ก็ยังตื่นเต้นเหมือนเดิม* ATLAS - รักกันวันเดียว ( ONE DAY ) | Prod. by URBOYTJ 🔗 #วันนี้ATLASบอกรักกันวันเดียว #ATLASรักกันวันเดียว #AtlasNextJourney #ATLAS_th #ATLASth #URBOYTJ

ATLASofficial

45,403 views • 3 years ago

And LIFTOFF of Atlas V Launches Amazon Leo LA-07!
0:18

And LIFTOFF of Atlas V Launches Amazon Leo LA-07!

Avid Space

14,287 views • 1 month ago