Search papers, labs, and topics across Lattice.
3
7
3
7
Flow Reversal Steering transforms vague human commands into precise robotic actions, achieving up to 95% higher success rates in real-world tasks with minimal training.
World models can now self-improve by identifying their own prediction errors, thanks to a clever decomposition of action-conditioned prediction into easier-to-verify components.
Q-functions and implicit policy extraction are game-changers for batch online RL in robotics, unlocking significant performance gains over imitation-based approaches.
