Sharon Zhou

TL;DR: Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.

TL;DR: This work establishes a gold standard human benchmark for generative realism by constructing Human eYe Perceptual Evaluation (HYPE), a human benchmark that is grounded in psychophysics research in perception, reliable across different sets of randomly sampled outputs from a model, able to produce separable model performances, and efficient in cost and time.

TL;DR: Inspired by a game-theoretic notion of incentive-compatibility, Boomerang opens opportunities for interaction design to incentivize honest reporting over strategic dishonesty.

TL;DR: This research advances computation as a powerful partner in establishing effective teamwork by introducing multi-armed bandits with temporal constraints: an algorithm that manages the timing of exploration--exploitation trade-offs across multiple bandits simultaneously.

TL;DR: In this paper, the authors synthesize results of different gap-filling methods systematically applied at 17 wetland sites spanning boreal to tropical regions and including all major wetland classes and two rice paddies.