MULTIMODAL AI - AI Dynamics

Creating Realistic Restaurant Environment Simulation

By

–

25 October 2023 0h54

Create your Environment We create a simple Restaurant, in our case a Chinese restaurant. With a nice vibe and quite busy with loads of people inside.

→ View original post on X — @linusekenstam

25 October 2023

Berkeley’s Nerfstudio generates 3D video, pursuing 4D interactions

By

@stanfordhai

–

24 October 2023 22h00

.
@UCBerkeley
’s @akanazawa offered an overview of her team’s Nerfstudio and all the ways they are generating 3D video. Her next challenge? “Generating 4D – interactions with things that are moving around – is my true passion.” Tune in here: http://
stanford.io/46NtzuT

→ View original post on X — @stanfordhai

24 October 2023

Language Models Discovering World Models for Biology Applications

By

@stanfordhai

–

24 October 2023 20h25

“With natural language, there’s a developing view that these models may be able to discover world models and simulate aspects of the world when trained on enough data. In biology, i think there’s an exciting potential for this.” @alexrives speaking at the 2023 HAI Fall Conference

→ View original post on X — @stanfordhai

24 October 2023

SALMONN Audio Upload Feature Now Available on Llama2.ai

By

@fofrai

–

24 October 2023 11h25

You can now upload audio files to https://t.co/pzYIjfx6GK to ask questions about them, using SALMONN. (It will only use the first 30 seconds)

@charliebholtz is fast! I also love the example. https://t.co/khhM5wlptk
— fofr (@fofrAI) 24 octobre 2023

You can now upload audio files to http://
llama2.ai to ask questions about them, using SALMONN. (It will only use the first 30 seconds) @charlieholtz is fast! I also love the example.

→ View original post on X — @fofrai

24 October 2023

AI Demo Outperforms Non-Heritage Japanese Language Learners

By

@patio11

–

24 October 2023 8h57

This demo is not perfect but outperforms probably four nines of all non-heritage Japanese majors in the U.S.

Yiiiiiiiiikes that was not on my bingo card for this year. https://t.co/JliMwyWFRY
— Patrick McKenzie (@patio11) 24 octobre 2023

This demo is not perfect but outperforms probably four nines of all non-heritage Japanese majors in the U.S. Yiiiiiiiiikes that was not on my bingo card for this year.

→ View original post on X — @patio11

24 October 2023

Cold War Origins of Modern Neural Networks and Their Persistent Biases

By

@timnitgebru

–

24 October 2023 0h29

"Today’s most advanced neural networks and sophisticated image-analysis methods come from 1950s and ’60s Cold War culture—and many biases and ways of understanding the world from that era persist along with them."

→ View original post on X — @timnitgebru

24 October 2023

Computer Vision: Algorithms, People, and Politics of Perception

By

@timnitgebru

–

24 October 2023 0h29

"The Birth of Computer Vision uncovers these histories and finds connections between the algorithms, people, and politics at the core of automating perception today."

→ View original post on X — @timnitgebru

24 October 2023