RESEARCH - AI Dynamics

A really nice paper by some of my Alphabet colleagues at Waymo about EMMA, the End-to-End Multimodal model that underlies much of the capabilities of the @Waymo cars. https://
storage.googleapis.com/waymo-uploads/
files/research/EMMA-paper.pdf
…

→ View original post on X — @jeffdean

31 October 2024

Building Large-Scale Clusters to Train and Release Llama

By

@soumithchintala

–

31 October 2024 4h06

its super fun to build very very large clusters, train llama on them, and release it for y'all to enjoy — and talk in great detail about how we did it!
It's also really fun to partner with @Ahmad_Al_Dahle in creating this disruptive chaos Join us, there's lots of work to do!

→ View original post on X — @soumithchintala

31 October 2024

Open Source TTS Model MaskGCT Released

By

@jiqizhixin

–

31 October 2024 3h43

introducing an opensource TTS model Masked Generative Codec Transformer (MaskGCT)!!!, https://
arxiv.org/abs/2409.00750 https://
github.com/open-mmlab/Amp
hion/tree/main/models/tts/maskgct
…

→ View original post on X — @jiqizhixin

31 October 2024

Non-Autoregressive TTS Model Eliminates Need for Alignment

By

@jiqizhixin

–

31 October 2024 3h43

a fully non-autoregressive TTS model that eliminates the need for explicit alignment information between text and speech supervision, as well as phone-level duration prediction

→ View original post on X — @jiqizhixin

31 October 2024

ROCKET-1: Visual-Temporal Prompting for Open-World Robot Interaction

By

@jiqizhixin

–

31 October 2024 3h37

ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting https://
arxiv.org/pdf/2410.17856
a low-level policy that predicts actions based on concatenated visual observations and segmentation masks, with real-time object tracking provided by SAM-2.

→ View original post on X — @jiqizhixin

31 October 2024