Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

Documenti analoghi

• EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning
  di: Chen, Yi, et al.
  Pubblicazione: (2023)
• DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA
  di: Chen, Yi, et al.
  Pubblicazione: (2026)
• Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
  di: Ge, Yuying, et al.
  Pubblicazione: (2024)
• DiCoDe: Diffusion-Compressed Deep Tokens for Autoregressive Video Generation with Language Models
  di: Li, Yizhuo, et al.
  Pubblicazione: (2024)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
  di: Chen, Yi, et al.
  Pubblicazione: (2025)