PulseAugur
LIVE 13:46:31
research · [1 source] ·
0
research

Generative Video WorldSim, Diffusion, Vision, Reinforcement Learning and Robotics — ICML 2024 Part 1

The Latent Space podcast released part one of its ICML 2024 recordings, focusing on generative video, vision, and robotics. The episode features discussions on OpenAI's Sora, Google DeepMind's award-winning Genie and VideoPoet models, and the broader field of generative video world simulators. It also touches upon diffusion models and the future of video generation beyond just scaling data. AI

Summary written by None from 1 source. How we write summaries →

RANK_REASON The cluster discusses research papers and models presented at ICML 2024, including award-winning work from Google DeepMind.

Read on Latent Space Podcast →

Generative Video WorldSim, Diffusion, Vision, Reinforcement Learning and Robotics — ICML 2024 Part 1

COVERAGE [1]

  1. Latent Space Podcast TIER_1 · Latent.Space ·

    Generative Video WorldSim, Diffusion, Vision, Reinforcement Learning and Robotics — ICML 2024 Part 1

    <p><em>Regular tickets are now sold out for </em><a href="https://lu.ma/LSLIVE" target="_blank"><em>Latent Space LIVE! at NeurIPS</em></a><em>! We have just announced our last speaker and newest track, friend of the pod </em><a href="https://www.latent.space/p/rlhf-201" target="_…