• Genie: Generative Interactive Environments with Ashley Edwards - #696

  • Aug 5 2024
  • Duração: 47 minutos
  • Podcast

Genie: Generative Interactive Environments with Ashley Edwards - #696

Ouça grátis

Ver detalhes do programa

  • Sumário

  • Today, we're joined by Ashley Edwards, a member of technical staff at Runway, to discuss Genie: Generative Interactive Environments, a system for creating ‘playable’ video environments for training deep reinforcement learning (RL) agents at scale in a completely unsupervised manner. We explore the motivations behind Genie, the challenges of data acquisition for RL, and Genie’s capability to learn world models from videos without explicit action data, enabling seamless interaction and frame prediction. Ashley walks us through Genie’s core components—the latent action model, video tokenizer, and dynamics model—and explains how these elements collaborate to predict future frames in video sequences. We discuss the model architecture, training strategies, benchmarks used, as well as the application of spatiotemporal transformers and the MaskGIT techniques used for efficient token prediction and representation. Finally, we touched on Genie’s practical implications, its comparison to other video generation models like “Sora,” and potential future directions in video generation and diffusion models. The complete show notes for this episode can be found at https://twimlai.com/go/696.
    Exibir mais Exibir menos
Política e Governo Ciências
Exibir mais Exibir menos
activate_samplebutton_t1

O que os ouvintes dizem sobre Genie: Generative Interactive Environments with Ashley Edwards - #696

Nota média dos ouvintes. Apenas ouvintes que tiverem escutado o título podem escrever avaliações.

Avaliações - Selecione as abas abaixo para mudar a fonte das avaliações.

Avaliações Audible.com.br

Avaliações na Amazon
Nenhuma revisão disponível