Tag
DroneWAM is an efficient world-action model for drone visual navigation that adopts a JEPA-based architecture to model future states directly in representation space, reducing computational costs. It introduces adaptive rollout to allocate prediction depth effectively and achieves best trajectory accuracy on the simulated DroneNav-6D dataset.
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.
The paper introduces Reinforced Planning, a method that learns to improve multi-step plans using latent world models, achieving near-perfect success in tasks like visual navigation and robotic manipulation with significantly higher efficiency than hand-designed algorithms.
UniNav is a unified world-action diffusion model for image-goal visual navigation that jointly predicts future visual observations and waypoint trajectories in a single diffusion process, achieving strong benchmark results with efficient inference.
Apple Research introduces Weblica, a framework for creating scalable and reproducible training environments for visual web agents using HTTP caching and LLM-based synthesis.