Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
6
0
8
0
GPT-6-Astra achieves unprecedented embodied intelligence performance, yet practical deployment faces significant hurdles in demonstration cost and physical constraints.
World models no longer require fragile offline reconstruction pipelines—baking native physics, depth, and camera pose directly into a unified multimodal generative process unlocks self-calibrating, closed-loop 3D spatial simulation at scale.
A single operator, aided by an MLLM-based agent, can achieve data collection success rates comparable to expert dual-human teams in complex multi-arm tasks.
Kairos achieves top-tier performance in Physical AI while ensuring efficient state management over extended time horizons, setting a new standard for operational world models.
Current text-to-CAD models can generate shapes, but they fail spectacularly when it comes to creating functional, manufacturable, and assemblable designs, as revealed by the new MUSE benchmark.
Multi-level preference alignment in SignDPO significantly reduces semantic drift, outperforming traditional gloss-free models and challenging gloss-based benchmarks.