@aiatmeta - AI Dynamics - Page 32 of 67

Meta Releases SAM 2 Open Source Visual Segmentation Model

By

–

23 August 2024 18h36

Segment Anything Model 2 (SAM 2) is a foundation model from Meta FAIR for promptable visual segmentation in images & videos.

Available now for anyone to build on for free, open source under an Apache license.

Try the demo ➡️ https://t.co/sTBToIR43x pic.twitter.com/iO1TlCej7x
— AI at Meta (@AIatMeta) 23 août 2024

Segment Anything Model 2 (SAM 2) is a foundation model from Meta FAIR for promptable visual segmentation in images & videos. Available now for anyone to build on for free, open source under an Apache license. Try the demo https://
go.fb.me/ve0y8o

→ View original post on X — @aiatmeta

23 August 2024

New Free Course on Improving LLM Applications Accuracy

By

@aiatmeta

–

22 August 2024 16h30

New course on @DeepLearningAI
: Improving Accuracy of LLM Applications https://
go.fb.me/zfwvd8 Created in collaboration with DL, Meta & @LaminiAI
, this free course covers topics like evaluation frameworks, instruction & memory fine-tuning, LoRA + training data generation.

→ View original post on X — @aiatmeta

22 August 2024

Spotify and Meta Support Clear AI Regulation for Innovation

By

@aiatmeta

–

21 August 2024 21h18

"Though Spotify and Meta use AI in different ways, we agree that thoughtful, clear and consistent regulation can foster competition and innovation while also protecting people and giving them access to new technologies that empower them."

→ View original post on X — @aiatmeta

21 August 2024

UniBench: Comprehensive Tools for VLM Model Evaluation

By

@aiatmeta

–

20 August 2024 20h07

We've published the comprehensive set of tools and scripts for evaluating VLM models and benchmarks in the UniBench repo

→ View original post on X — @aiatmeta

20 August 2024

Meta FAIR Introduces UniBench: Unified VLM Benchmark Suite

By

@aiatmeta

–

20 August 2024 20h06

New research from Meta FAIR: UniBench is a unified implementation of 50+ VLM benchmarks spanning a comprehensive range of carefully categorized capabilities from object recognition to spatial awareness, counting and much more. Research paper https://
go.fb.me/fa97z9

→ View original post on X — @aiatmeta

20 August 2024

Meta AI Launches Personalized Image Generation Without Fine-Tuning

By

@aiatmeta

–

19 August 2024 19h59

Research paper from GenAI at Meta: Imagine yourself: Tuning-Free Personalized Image Generation. Research paper https://
go.fb.me/wre8f0 Want to try it? The feature is available now as a beta in Meta AI for users in the US.

→ View original post on X — @aiatmeta

19 August 2024

Meta accelerates machine learning developer productivity

By

@aiatmeta

–

15 August 2024 21h40

A closer look at how we're enabling greater developer velocity for machine learning work at Meta.

→ View original post on X — @aiatmeta

15 August 2024

NVIDIA Refines Llama 3.1 8B into Minitron 4B Model

By

@aiatmeta

–

15 August 2024 19h19

Using structured weight pruning and knowledge distillation, the @NVIDIAAI research team refined Llama 3.1 8B into a new Llama-3.1-Minitron 4B. They're releasing the new models on @huggingface and shared a deep dive on how they did it https://
go.fb.me/b2h2c8

→ View original post on X — @aiatmeta

15 August 2024

European AI Startups: Last Call for 4-Month Accelerator Program

By

@aiatmeta

–

14 August 2024 19h51

Last call — applications close this Friday https://
go.fb.me/cl9rjs This 4-month AI accelerator is designed for European startups developing advanced AI solutions with open-source foundation models. Our aim is to accelerate the development and market entry of these projects.

→ View original post on X — @aiatmeta

14 August 2024