The method is general .

This work was conducted at Microsoft.

In mental state decoding, researchers aim to identify certain mental states (e.g., deciding to accept or

The result of PC 2 vs. PC 3 (Figure 1) suggests that the first quadrant represents concepts describing

It has been shown that network pruning ( Han et al., 2015) is an effective technique to reduce the

Most current models use deterministic attention modules due to their simplicity and ease of optimization. Stochastic counterparts, on the other hand, are less popular despite their potential benefits.