Meta VR Glasses(meta.com)

458 points by polymorph1sm 1 month ago | 416 comments

Meta product page announcing Meta VR Glasses, coming Spring 2027 for $1,299, with an email signup form for launch notifications.

Emu Video and Emu Edit, our latest generative AI research milestones(ai.meta.com)

183 points by ot 2 years ago | 40 comments

The Seamless Communication models(ai.meta.com)

678 points by skadamat 2 years ago | 329 comments

Meta AI research page for Seamless Communication, a family of AI translation models for expressive, fast speech and text translation, with model downloads.

Meta introduces Segment Anything Model 2(ai.meta.com)

240 points by bambax 2 years ago | 68 comments

Llama 3.1 Official Launch(llama.meta.com)

138 points by luiscosio 2 years ago | 53 comments

Requesting SDK for Meta Ray-Ban Smart Glasses for Visually Impaired Users(communityforums.atmeta.com)

48 points by walterbell 1 year ago | 6 comments

Meta 3D Gen(ai.meta.com)

455 points by meetpateltech 2 years ago | 128 comments

Meta AI research publication page for Meta 3D Gen, a system for generating 3D assets, dated July 2, 2024, with abstract and author list.

Sora: Creating video from text(openai.com)

3541 points by davidbarker 2 years ago | 2161 comments

OpenAI's announcement page for Sora, an AI model that generates realistic and imaginative videos from text instructions.

NeuralSVG: An Implicit Representation for Text-to-Vector Generation(sagipolaczek.github.io)

726 points by lnyan 1 year ago | 69 comments

Project page for NeuralSVG, a research method from Tel Aviv University and MIT CSAIL that generates layered SVG vector graphics from text prompts using an implicit neural representation.

Meta AI announces Massive Multilingual Speech code, models for 1000+ languages(github.com)

615 points by crakenzak 3 years ago | 193 comments

GitHub directory in Meta's fairseq repository containing code and models for Massive Multilingual Speech (MMS), covering ASR, TTS, and language ID for 1000+ languages.

How Meta trains large language models at scale(engineering.fb.com)

362 points by mfiguiere 2 years ago | 183 comments

Engineering at Meta blog post describing the software, hardware, and network considerations behind training large language models at scale in production.

MeshGPT: Generating triangle meshes with decoder-only transformers(nihalsid.github.io)

684 points by jackcook 2 years ago | 148 comments

Project page for MeshGPT, a research paper from TU Munich, Politecnico di Torino and Audi that generates triangle meshes using decoder-only transformers.