AI - AI Dynamics

→ View original post on X — @officialindiaai

Lab2Market 2023 Winners Connect Academic Innovation with Industry

By

@officialindiaai

–

31 May 2023 8h11

Lab2Market aims to connect academic innovators with industry professionals to maximise the impact of their work. Our initiative recognizes exceptional researchers and their groundbreaking projects. Without further ado, let's meet the outstanding winners of Lab2Market 2023.

VisorGPT: Learning Visual Prior via Generative Pre-Training

By

–

31 May 2023 8h05

VisorGPT: Learning Visual Prior via Generative Pre-Training

propose to learn Visual prior via Generative Pre-Training, dubbed VisorGPT. By discretizing visual locations of objects, e.g., bounding boxes, human pose, and instance masks, into sequences, our~can model visual prior… pic.twitter.com/xj84MvpE14
— AK (@_akhaliq) 31 mai 2023

VisorGPT: Learning Visual Prior via Generative Pre-Training propose to learn Visual prior via Generative Pre-Training, dubbed VisorGPT. By discretizing visual locations of objects, e.g., bounding boxes, human pose, and instance masks, into sequences, our~can model visual prior

LibriTTS-R: Restored Multi-Speaker Text-to-Speech Dataset

By

–

31 May 2023 8h01

LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus paper introduces a new speech dataset called “LibriTTS-R'' designed for text-to-speech (TTS) use. It is derived by applying speech restoration to the LibriTTS corpus, which consists of 585 hours of speech data at 24 kHz

→ View original post on X — @mrgreen

Photoshop AI Feature Enables Single-Click Image Manipulation

By

@mrgreen

–

31 May 2023 7h59

Thanks to Photoshop's new AI feature you can go from 'we' to 'me' in just one click." pic.twitter.com/ROoWayoC7P
— Lorenzo Green 〰️ (@mrgreen) 31 mai 2023

Thanks to Photoshop's new AI feature you can go from 'we' to 'me' in just one click."

AlteredAvatar: Fast Style Adaptation for Dynamic 3D Avatars

By

–

31 May 2023 7h58

AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptation

presents a method that can quickly adapt dynamic 3D avatars to arbitrary text descriptions of novel styles. Among existing approaches for avatar stylization, direct optimization methods can produce excellent… pic.twitter.com/k9uhlZhWz0
— AK (@_akhaliq) 31 mai 2023

AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptation presents a method that can quickly adapt dynamic 3D avatars to arbitrary text descriptions of novel styles. Among existing approaches for avatar stylization, direct optimization methods can produce excellent

Geometric Algebra Transformers: A New Architecture for Geometric Data

By

–

31 May 2023 7h29

Geometric Algebra Transformers introduce the Geometric Algebra Transformer (GATr), a general-purpose architecture for geometric data. GATr represents inputs, outputs, and hidden states in the projective geometric algebra, which offers an efficient 16-dimensional vector space

→ View original post on X — @midjourney

Midjourney launches billing support email service

By

@midjourney

–

31 May 2023 6h26

we have a billing support email on our website now billing@midjourney.com pls give them a ring and they should be able to help with any issues

Grammar Prompting for Domain-Specific Language Generation with LLMs

By

–

31 May 2023 6h04

Grammar Prompting for Domain-Specific Language Generation with Large Language Models Large language models (LLMs) can learn to perform a wide range of natural language tasks from just a handful of in-context examples. However, for generating strings from highly structured

LANCE: Stress-testing Visual Models with Language-guided Counterfactual Images

By

–

31 May 2023 6h01

LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images propose an automated algorithm to stress-test a trained visual model by generating language-guided counterfactual test images (LANCE). Our method leverages recent progress in large language