Search Results for author:
Found 4 papers, 1 papers with code
From Language Models to Practical Self-Improving Computer Agents
Rather than manually developing static software to augment LLMs through human engineering effort, we propose that an LLM agent can systematically generate software to augment itself.
Task Transfer and Domain Adaptation for Zero-Shot Question Answering
Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks.
Self-Programming Artificial Intelligence Using Code-Generating Language Models
Prior work in meta-learning and neural architecture search has led to substantial successes across various task domains, spawning myriad approaches for algorithmically optimizing the design and learning dynamics of deep learning models.
Distributed Evolution Strategies Using TPUs for Meta-Learning
Our contributions are twofold: we provide the first assessment of evolutionary meta-learning in a supervised setting, and create a general framework for distributed evolution strategies on TPUs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
