19min chapter

Latent Space: The AI Engineer Podcast — Practitioners talking LLMs, CodeGen, Agents, Multimodality, AI UX, GPU Infra and all things Software 3.0 cover image

2024 in Vision [LS Live @ NeurIPS]

Latent Space: The AI Engineer Podcast — Practitioners talking LLMs, CodeGen, Agents, Multimodality, AI UX, GPU Infra and all things Software 3.0

CHAPTER

Advancements in Vision-Language Models

This chapter examines the current trends and limitations in large-scale inference models, specifically focusing on visual recognition capabilities of large language models (LLMs). It discusses the need for benchmarking and pre-training to enhance model performance, as well as introduces innovative models like Florence 2 and Polygema 2 that aim to improve object detection and semantic understanding. The chapter also highlights a novel transformer approach that optimizes image processing and fine-grained feature learning without relying on extensive annotations.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode