Thank you @davidchalmers42 for featuring https://
minedojo.org in your talk. We build open-ended agents that can solve any task in Minecraft. This requires the agent to have awareness of the Minecraft world. Foundation models provide the agent with priors (e.g. reward function)
OPEN SOURCE
-
MineDojo: Open-ended Agents for Minecraft Task Solving
By
–
-
BigCode Event: A Great Community Experience
By
–
A great pleasure! Thanks for stopping by the BigCode event
-
Compression Enhances Generalization in Multilingual NER Models
By
–
Intriguing Properties of Compression on Multilingual Models. This paper finds that compression confers several interesting & prev. unknown generalization properties on mBERT NER models. Kelechi Ogueji, Orevaoghene Ahia, @lekeOnilude
, Sebastian Gehrmann, @SaraHookr
, @KreutzerJulia -
Apple optimizes Stable Diffusion for Silicon with Core ML
By
–
Honored to support Apple with our @diffuserslib code and Hub They built a heavily optimized Core ML version of SD that runs on Apple Silicon. And they think < 1s is within reach using distillation
Read the short blog post -> https://
hf.co/blog/diffusers
-coreml
… -
Fighting for Open AI Systems Against Closed Approaches
By
–
Don't lose hope! It's always a pendulum between closed and open and very cool open stuff will follow if we keep fighting for it like you've been doing!
-
Stable Diffusion 2: Foundational Model Powering Next Generation
By
–
Perhaps @StableDiffusion 2 was misnamed. the “2” branding implies it’s same but better, but it’s not – out of the box. it’s a LOT better when you know how to wield it, or finetune it. SD2 is a *foundational* model now, that will power an entire generation of txt2img models.
-
Interactive Language Framework Enables Real-Time Language-Conditionable Robots
By
–
Interactive Language is an imitation learning framework for producing real-time, open vocabulary language-conditionable robots. Learn more and check out the newly released and largest available language-annotated robot dataset, called Language-Table → https://t.co/ZdQCeYEFJl pic.twitter.com/5zMyoa9B57
— Google AI (@GoogleAI) 1 décembre 2022Interactive Language is an imitation learning framework for producing real-time, open vocabulary language-conditionable robots. Learn more and check out the newly released and largest available language-annotated robot dataset, called Language-Table → http://
bit.ly/3Umujjt -
Ludwig AI Poster at PyTorch Conference NeurIPS 2022
By
–
Headed to #PyTorchConference at #neurips2022 tomorrow? Check out Predibase founding engineer Justin Zhao's poster on http://
Ludwig.ai. Justin will share how @ludwig_ai makes it easy to build end-to-end #ML pipelines with a config-driven approach. http://
pbase.ai/pytorchconf22 -
LangChain 0.0.26: Stop Tokens and Document Question Answering
By
–
LangChain version 0.0.26: More flexible support for stop tokens (idea from @prof_reed
) Document Question Answering with Sources (lots of help from @johnjnay
) See below for a deep dive on the later! -
LangChain Plans to Integrate Weaviate into Library
By
–
Hearing a lot about @weaviate_io recently! Need to integrate them into the library