GPT Reviews
Meta is testing an AI-powered search bar in Instagram, which could improve the quality of search and help users discover new content on the platform.
Grok-1.5V is a new multimodal model that can process a wide variety of visual information and outperforms its peers in the new RealWorldQA benchmark.
"Scaling (Down) CLIP" explores the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets, and shows that smaller datasets and models can still achieve comparable performance.
"Pre-training Small Base LMs with Fewer Tokens" investigates a simple approach called Inheritune to develop a small base language model (LM) from a larger existing LM, which can effectively match the val loss of their bigger counterparts when trained from scratch for the same number of training steps.
Contact:Β Β sergi@earkind.com
Timestamps:
00:34 Introduction
01:40Β Meta is testing an AI-powered search bar in Instagram
03:02Β Grok-1.5 Vision Preview
04:56Β Visualizing Attention, a Transformer's Heart
06:12 Fake sponsor
08:27Β Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
10:11Β Pre-training Small Base LMs with Fewer Tokens
11:58Β Flying with Photons: Rendering Novel Views of Propagating Light
13:57 Outro