NVIDIA's Jim Fan declared the end of Visual-Language-Action (VLA) models and remote operation in robotics, advocating for World Action Models (WAM) as the new paradigm. Fan proposed that WAMs, inspired by Large Language Models (LLMs), will leverage next-state prediction and action fine-tuning for robot control. He emphasized a shift towards using first-person human video data as the primary training source, moving away from the limitations of remote operation data collection. AI
IMPACT This commentary signals a potential shift in robotics research and development, moving towards new model architectures and data strategies.
RANK_REASON This is a commentary on the future of robotics by a prominent researcher, not a direct model release or product announcement.
- Andrej Karpathy
- DreamDojo
- Dream Zero
- EgoScale
- Elon Musk
- Jensen Huang
- Jim Fan
- LLM
- NVIDIA
- Robotics: Endgame
- Sunday
- Taylor Swift
- WAM
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
