Shuo Wang

Real-time neural SLAM on a mobile robot is now achievable with state-of-the-art accuracy, bridging the gap between geometric efficiency and neural implicit mapping.

Raw plasma flux can be converted into continuous macroscopic torque with orders-of-magnitude higher efficiency and power than conventional liquid active matter, sustaining coherent rotation down to a single particle.

Chain-of-thought context can be halved without sacrificing accuracy by using the geometric trajectory of hidden states to selectively compress exploratory reasoning steps into continuous latent tokens.