Search papers, labs, and topics across Lattice.
5
0
6
Expert calibration alone isn't enough for soft-routed MoE models; an innovative adversarial reweighting approach is needed to tackle distribution shifts effectively.
Energy-guided diffusion models can bridge the gap between source and target domains in off-dynamics offline RL, enabling effective trajectory generation without retraining the diffusion model.
Ditching aggregated time series, AeroSense predicts air traffic flow with higher fidelity by directly modeling the dynamic set of individual aircraft states.
Autonomous driving planners can now explicitly self-correct unsafe actions by generating motion-token traces conditioned on a learned collision critic, leading to significant safety improvements.
Achieve safe RL exploration from day one without conservative optimization or hyperparameter tuning, by probabilistically regulating a new policy based on a safe reference policy.
