Louis-François Bouchard, aka What's AI

Imagic: Manipulate images using pre-trained image generator models!

How AI generates 3d models from only text!

A good transcription tool that would accurately understand what you say and write it down

Generates videos from text!

What does such a model understand when it sees such a picture or, even more complex, a video?

Personalizing Text-to-Image Generation using Textual Inversion

A New Challenging Task for AI: panoptic scene graph generation

A High-Resolution Image Synthesis Architecture: Latent Diffusion

"Make-A-Scene": a fantastic blend between text and sketch-conditioned image generation.

DALL·E 2 Pre-Training Mitigations

They reconstruct sound using cameras and a laser beam on any vibrating surface, allowing them to isolate music instruments, focus on a specific speaker, remove ambient noises, and many more amazing applications.

The beginning of data-centric AI with data programming

Translating 200 languages with a single model - Meta AI

Dalle mini is a free, open-source AI that produces amazing images from text inputs. Here's how it works.

An AI that creates photorealistic images from input text better than Dall-e 2!

How can Uber deliver food and always arrive on time or a few minutes before?

Gato: A single Transformer to RuLe them all! The first generalist RL agent using transformers!

A GAN model that uses simple blobs to manipulate objects in images…

An open-source model that is as powerful as GPT-3!

This AI can reconstruct, enhance and edit your images!

A new model for automatically generating summaries using machine learning, released in Google Docs that you can already use!

An amazing new model by OpenAI capable of generating and inpainting images from a text input with incredible results!

Instant NeRF by NVIDIA Research explained simply

Combine Lidar and regular Cameras for 3D object detection - Waymo & Google Research