Qiming Yuan

TL;DR: It is demonstrated that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot, made possible by a novel algorithm, which is called automatic domain randomization (ADR), and a robot platform built for machine learning.

TL;DR: It is shown that contrastive pre-training on unsupervised data at scale leads to high quality vector representations of text and code.

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: In this paper, the authors train a single goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects, without any human priors.

TL;DR: Using functional magnetic resonance imaging and transcranial direct current stimulation, brain activation showed the bilateral posterolateral cerebellum was associated with bilingual language control, and an effective connectivity analysis built brain networks for the interaction between the Cerebellum and the cerebral cortex.