LDA-1B: Unified World Model Trained on 30k Hours of Robot Data
chris_j_paxton · x · 2026-08-24
LDA-1B is a unified foundation model trained on 30,000 hours of human and robot interaction data. Instead of choosing between a world model and a language-conditioned policy, LDA-1B jointly learns forward dynamics, action prediction, and visual forecasting within a structured DINO latent space. This avoids pitfalls of pixel-level prediction, works on both dexterous hands and simple grippers, and generalizes across objects and tasks.
Related event: LDA-1B: unified robot world model trained on 30k hours(4 posts)→
More from Embodied
- Reachy Mini Chat App Weekend: $390 Infra vs. $4K+ GPT — andimarafioti · 2026-08-24
- Humanoid Business is About Maintenance, Not One-Time Sales — demian_ai · 2026-08-24
- Jarvis voice AI skill update: you can now talk to your ROS-powered robots — chrismatthieu · 2026-08-24
- Opinion: China is the World Leader in Humanoid Robotics by a Mile — LinusEkenstam · 2026-08-24
- Pure reinforcement learning enables zero-shot robot transfer — chris_j_paxton · 2026-08-24
- Humanoid Robot Cleaning Service Launches in SF for $30/hr — Olivier__OG · 2026-08-24