Search papers, labs, and topics across Lattice.
4
0
7
Understanding the right types of uncertainty for dynamical systems could revolutionize how we model and predict complex behaviors in AI.
Neuromorphic hardware can now continually learn new actions from event camera data with 100x energy reduction and 16x lower latency compared to edge GPUs.
ProxySHAP slashes the computational cost of Shapley interaction estimation while simultaneously boosting accuracy, finally making high-order interaction analysis practical for models with thousands of features.
Credal sets, previously impractical for large models, are now efficiently computable via a "decalibration" method that delivers strong performance in uncertainty-aware tasks.
