Tag
This paper proposes a Latent World Model (LWM) for robot navigation that predicts action-conditioned latent feature compatibility, enabling policy learning from unlabeled video data and reinforcement learning without additional environment interaction, outperforming existing methods.
This paper introduces a mechanistic interpretability approach to steer LLM personality traits by identifying and intervening on latent features using sparse autoencoders, achieving controllable personality modulation while maintaining language performance.