SearcharxivSearch

arXiv subjects

Jiayao Zhao

Publications and source records attributed to Jiayao Zhao.

2 recordsLinked to original sources

GLAM: Training a latent world model over global spatiotemporal memory for active exploration and navigation

Active exploration and semantic navigation require an embodied agent to build memory from partial observations, predict how the evolution of observed spatial memory may support future motion, and convert that prediction into actionable plans. We present GLAM, a goal-conditioned latent world model trained over global spatiotemporal memory, and GLAM NAV, the complete navigation system built around it. Given historical map tokens, a navigation goal, and the current robot pose, GLAM jointly predicts future map representations and robot-centric waypoint latents, allowing future spatial context and navigation intent to be inferred in a shared representation space. The model follows a JEPA-like latent prediction paradigm, operates directly on map-level latent tokens rather than RGB reconstruction, and uses a pretrained waypoint encoder-decoder to supervise and decode navigation plans within GLAM NAV. Training data are collected by replaying ObjectNav expert trajectories in Habitat over HM3D v0.2 scene assets and slicing them into multi-timescale prediction samples. On a controlled HM3D-ObjectNav subset reproduction setting, GLAM NAV improves over a reproduced BSC-Nav baseline in both success rate and success weighted by path length.

cs.RO

Exotic equilibration dynamics on a 1-D quantum CNOT gate lattice

We consider the dynamics of local entropy and nearest neighbor mutual information of a 1-D lattice of qubits via the repeated application of nearest neighbor CNOT quantum gates. This is a quantum version of a cellular automaton. We analyze the entropy dynamics for different initial product states, both for open boundary conditions, periodic boundary conditions and we also consider the infinite lattice thermodynamic limit. The dynamics gives rise to fractal behavior, where we see the appearance of the Sierpinski triangle both for states in the computational basis and for operator dynamics in the Heisenberg picture. In the thermodynamics limit, we see equilibration with a time dependence controlled by $\exp(-αt^{h-1})$ where $h$ is the fractal dimension of the Sierpinski triangle, and $α$ depends on the details of the initial state. We also see log-periodic reductions in the one qubit entropy where the approach to equilibrium is only power law. For open boundary conditions we see time periodic oscillations near the boundary, associated to subalgebras of operators localized near the boundary that are mapped to themselves by the dynamics.

quant-ph