Search papers, labs, and topics across Lattice.
Australian Institute for Machine Learning, Adelaide University
5
1
7
8
Agentic control in zero-shot navigation rivals industrial-scale policies, achieving up to 78% success with minimal interfaces and fewer resources.
Automated architecture search can enhance embodied agent performance, but it also reveals critical challenges that could hinder optimization.
One model to control them all: Qwen-VLA achieves impressive zero-shot generalization across diverse robotic tasks and embodiments by unifying vision-language-action modeling.
Generative video models can now simulate a continuously evolving world, even when objects are out of sight, thanks to a new framework that maintains persistent global state.
VLNVerse tackles the sim-to-real gap in vision-language navigation by providing a unified, large-scale benchmark with realistic physics simulation and full-kinematics embodied agents.
