Meta's CM3leon 🎨 // ChatGPT Isn't Getting Dumber 🤔 // Linear Complexity Speech Recognition 🗣️
Description
CM3leon, a new generative model for text and images that is more efficient and state-of-the-art. OpenAI researcher Jason Wei is also featured, offering an "Ask Me Anything" document on AI research. Additionally, Sumformer, a linear-complexity alternative to self-attention for speech recognition, and DreamTeacher, a self-supervised feature representation learning framework that uses generative networks for pre-training downstream image backbones, are discussed.
Contact: sergi@earkind.com
Timestamps:
00:34 Introduction
02:16 Introducing CM3leon, a more efficient, state-of-the-art generative model for text and images
03:40 OpenAI product leader denies claims GPT-4 has gotten ‘lazier and dumber’
05:12 Jason Wei (OpenAI Researcher) tweets
06:04 Fake sponsor
07:54 Sumformer: A Linear-Complexity Alternative to Self-Attention for Speech Recognition
09:05 NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis
10:19 DreamTeacher: Pretraining Image Backbones with Deep Generative Models
12:15 Outro
United States
