Clemens Winter

TL;DR: GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.

TL;DR: This article showed that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches.

TL;DR: Codex as discussed by the authors is a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities, showing that repeated sampling from the model is a surprisingly effective strategy for producing working solutions to difficult prompts.

TL;DR: This poster presents a probabilistic procedure for solving phase equilibria calculations of mixtures with known coefficients, and demonstrates the ability of this procedure to resolve the uncertainty in the values of the coefficients.

TL;DR: The authors proposed a generalization-first approach to learn to update optimizer hyperparameters instead of model parameters directly using novel features, actions, and a reward function, which achieved 2x speedups on ImageNet and a 2.5x speedup on a language modeling task using over 5 orders of magnitude more compute than the training tasks.