Search papers, labs, and topics across Lattice.
4
0
9
Nighttime off-road driving just got a whole lot safer: a new dataset and method overcome the limitations of visible-light perception by leveraging infrared data and temporal context.
Transfer learning can unlock scalable emission control across diverse waste incineration plants by learning transferable system-level structures that capture physical constraints, operating-regime heterogeneity, and carbon-pollutant coupling.
Zero-shot sim-to-real transfer for quadrotor control is now systematically achievable, thanks to a unified framework that integrates differentiable physics learning with training, validation, and real-world deployment.
Iterative visual refinement lets agents navigate dense coding IDEs with superhuman precision, outperforming single-shot methods and paving the way for more reliable software engineering agents.
