Search papers, labs, and topics across Lattice.
5
0
6
Hy-Embodied-VLM-1.0 outperforms its predecessor by 8.4% while activating only a fraction of the parameters, redefining efficiency in embodied agents.
ViQ achieves a groundbreaking balance between semantic richness and detail in visual representations, enabling efficient multimodal training without sacrificing quality.
A fully integrated robot learning stack that bridges the gap from simulation to real-world deployment, enhancing the efficacy of vision-language-action models.
Teaching VLMs to predict depth maps during pre-training unlocks surprisingly large gains in real-world robot task execution.
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.
