More details, including links to the research paper, model weights and code
@aiatmeta
-
Meta Spirit LM: Open Source Multimodal Language Model for Text and Speech
By
–
Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech.
— AI at Meta (@AIatMeta) 18 octobre 2024
Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches… pic.twitter.com/gMpTQVq0nEToday we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches
-
Meta FAIR Releases Eight New AI Research Artifacts for Open Science
By
–
Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from @jpineau1.
— AI at Meta (@AIatMeta) 18 octobre 2024
This work is another important step… pic.twitter.com/o43wgMZmzKOpen science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from @jpineau1
. This work is another important step -
Meta Open Sources Movie Gen Bench for Audio Video Generation
By
–
As detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models.
— AI at Meta (@AIatMeta) 17 octobre 2024
Movie Gen Video Bench… pic.twitter.com/66aOaIGwwRAs detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models. Movie Gen Bench
-
Meta Movie Gen pilot results with Blumhouse and creators
By
–
Today, we’re sharing initial results from our work with @Blumhouse and select creators as we continue to develop our Meta Movie Gen models. We’re excited to expand this pilot program in collaboration with the creative industry in 2025 https://
go.fb.me/0qzo8m -
Meta Releases CoTracker3 for Improved Point Tracking in Videos
By
–
New AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos.
— AI at Meta (@AIatMeta) 16 octobre 2024
More details ➡️ https://t.co/CUduYnp0sU
Demo on @huggingface ➡️ https://t.co/2BxvVrBk0e
Building on our previous work on CoTracker, this new model demonstrates impressive… pic.twitter.com/eQ2ZRNQDrnNew AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. More details https://
go.fb.me/xiyc63
Demo on @huggingface https://
go.fb.me/yzuqd0 Building on our previous work on CoTracker, this new model demonstrates impressive -
Lenovo Launches AI Now, On-Device Agent Built on Llama 3.1
By
–
Announced today — Lenovo AI Now is a new on-device AI agent, built with Llama 3.1 to enable capabilities ranging from document management and summarization, to device control and content generation. Exciting to see this kind of AI innovation from the team at @Lenovo
. -
Meta Movie Gen: 13B Audio Generation Model for Video Synthesis
By
–
As part of Meta Movie Gen, we trained a 13B parameter audio generation model that can take a video + optional text prompts to generate high quality audio — including ambient sound, foley & instrumental background music — all synced to the video. Details https://
go.fb.me/vgkswc -
Movie Gen Models and Capabilities Details Shared
By
–
We’ve shared more details on the models and Movie Gen capabilities in a new blog post ➡️ https://t.co/J1dwK6p1jT pic.twitter.com/w0U3WZxmLm
— AI at Meta (@AIatMeta) 4 octobre 2024We’ve shared more details on the models and Movie Gen capabilities in a new blog post https://
go.fb.me/4b6eii -
Meta Movie Gen: Video Generation, Editing, and Audio Capabilities
By
–
More examples of what Meta Movie Gen can do across video generation, precise video editing, personalized video generation and audio generation. pic.twitter.com/Dz65QGNgaJ
— AI at Meta (@AIatMeta) 4 octobre 2024More examples of what Meta Movie Gen can do across video generation, precise video editing, personalized video generation and audio generation.