Search Results for author:
Found 3 papers, 1 papers with code
Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
More concretely, in this paper we ask: Given a hidden (internal) representation of a single token at position $t$ in an input, can we reliably anticipate the tokens that will appear at positions $\geq t + 2$?
Dropout Attacks
DROPOUTATTACK attacks the dropout operator by manipulating the selection of neurons to drop instead of selecting them uniformly at random.
Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
We develop the first non-trivial lower bound on the worst-case error of the best map from attributes to classes for this setting, even with perfect attribute detectors.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
