MULTIMODAL AI - AI Dynamics

Top ML Papers Week: AlphaDev, MusicGen, RLHF Advances

By

–

11 June 2023 15h57

Top ML Papers of the Week (June 5-11): – AlphaDev
– MusicGen
– Fine-Grained RLHF
– Humor in ChatGPT
– Concept Scrubbing in LLM
– Augmenting LLMs with Databases
…

→ View original post on X — @dair_ai

11 June 2023

Dense Motion Estimation Method Tracks Pixels Across Full Videos

By

@dair_ai

–

11 June 2023 15h57

1/ Tracking Everything Everywhere All at Once – propose a test-time optimization method for estimating dense and long-range motion; enables accurate, full-length motion estimation of every pixel in a video.https://t.co/7O3Z0Em7wE
— DAIR.AI (@dair_ai) 11 juin 2023

1/ Tracking Everything Everywhere All at Once – propose a test-time optimization method for estimating dense and long-range motion; enables accurate, full-length motion estimation of every pixel in a video.

→ View original post on X — @dair_ai

11 June 2023

MusicGen, BAAI LLM, LIMA Dataset, Llama Falcon Variants

By

@reach_vb

–

11 June 2023 13h03

MusicGen, BAAI’s new LLM, LIMA dataset launch, a billion new variants of Llama/ Falcon & much more.

You were missed hehe! 🤗 pic.twitter.com/rg2mF0hk7U
— Vaibhav (VB) Srivastav (@reach_vb) 11 juin 2023

MusicGen, BAAI’s new LLM, LIMA dataset launch, a billion new variants of Llama/ Falcon & much more. You were missed hehe!

→ View original post on X — @reach_vb

11 June 2023

Keanu Reeves as Superhero in Taiwanese Night Market via Midjourney

By

@christinelu

–

11 June 2023 5h27

I asked for Keanu Reeves as a superhero in a Taiwanese night market buying snack. Greg Hildebrandt comic artist style. I guess AI knows Keanu doesn’t need a costume to be a superhero. #midjourney

→ View original post on X — @christinelu

11 June 2023

NYC Rat Documentary Created with Text to Video AI Modelscope

By

@_akhaliq

–

11 June 2023 4h47

NYC Rat Documentary, text to video AI, Modelscope pic.twitter.com/Zvtn44iVTy
— AK (@_akhaliq) 11 juin 2023

NYC Rat Documentary, text to video AI, Modelscope

→ View original post on X — @_akhaliq

11 June 2023

Word-As-Image for Semantic Typography in Machine Learning

By

@miketamir

–

10 June 2023 17h37

Word-As-Image for Semantic Typography https://
bit.ly/3MI8bjk #MachineLearning #AI #DataScience #DeepLearning

→ View original post on X — @miketamir

10 June 2023

Real-Time Model Inference Streaming for Low-Latency AI Applications

By

@avikumart_

–

10 June 2023 16h30

Streaming is typically used when the data is arriving in real time, or when the latency requirements are very low. A typical example of this kind of model inference is the social media feeds, movie recsys, etc.

→ View original post on X — @avikumart_

10 June 2023

PandaGPT: Multimodal AI Model for Vision, Audio, Text Tasks

By

@marktabnet

–

10 June 2023 16h07

PandaGPT is a general-purpose instruction-following model that can both see and hear. PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questions about audios. https://
bit.ly/45TnAVl

→ View original post on X — @marktabnet

10 June 2023

QR Codes Meet Stable Diffusion: AI Vision Evolution

By

@clementdelangue

–

10 June 2023 15h36

I never imagined QR codes & Stable diffusion would collide. They seem to be from such different worlds! Funny story, 11 years ago, I tried to make a point that QR codes will be made useless thanks to computer vision: https://
youtube.com/watch?v=8iPgYV
-__mo
…. Guess I was wrong!

→ View original post on X — @clementdelangue

10 June 2023