Starry Era CEO Chen Jianyv proposes a shift in embodied AI from Vision-Language-Action (VLA) models to world models. While VLA focuses on imitating human actions, world models aim to understand and predict the physical world's dynamics, enabling greater generalization for robots. Chen highlighted that this approach, powered by video prediction, offers a more robust foundation for robots to tackle novel tasks and interact with complex environments, moving beyond mere imitation. AI
IMPACT Proposes a new paradigm for embodied AI, potentially leading to more generalizable and capable robots that can understand and interact with the physical world.
RANK_REASON The article reports on a CEO's perspective and proposed paradigm shift in embodied AI, rather than a direct product release or research breakthrough.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
