In particular, the non-linear model is often optimized, whereas the reference KF model is not. We argue that both should be optimized similarly, and to that end present the Optimized KF ( OKF).

Both challenges involve modeling long-term dependencies.

Over time, the two branches interact recurrently to build a scene representation from moving fixations.

We propose and empirically validate a scaling law for compute optimality that accounts for the decreasing value of repeated tokens and excess parameters.

Learning continuous-time point processes is essential to many discrete event forecasting tasks.

Images generated using Stable Diffusion v2.1 [