Search papers, labs, and topics across Lattice.
5
0
7
3
RoboDawn is investigated, a human-intuitive interface that exposes robotic control to an agentic VLM through a compact set of discrete translation, rotation, and gripper commands, and an in-context learning (ICL) scheme is introduced that ground the VLM in both interface usage and task-solving strategies.
Hy-Embodied-VLM-1.0 outperforms its predecessor by 8.4% while activating only a fraction of the parameters, redefining efficiency in embodied agents.
GUICrafter achieves superior GUI agent performance with just a fraction of the data, revolutionizing the way we think about training in data-scarce environments.
Real-world robots get a serious upgrade with HY-Embodied-0.5, a VLM family that rivals Gemini 3.0 Pro in embodied reasoning while also offering a deployable 2B parameter version.
Achieve SOTA in long-horizon spatial understanding by training a model to streamingly maintain and update spatial evidence from video via test-time adaptation of fast weights.
