Hiroaki Hayashi is a Senior Research Scientist at Salesforce AI Research, focusing on LLMs for code, software engineering LLM agents, and interactivity in LLM. Previously he obtained his PhD at Carnegie Mellon University in 2021 with a focus on natural language generation.
Large language model (LLM)-based software engineering (SWE-) agents have recently demonstrated remarkable progress on realistic software engineering tasks such as code review, bug fixing, and repository-level reasoning. Most SWE-agents start from a fresh…
Equal contribution between Erik Nijkamp and Hiroaki Hayashi. PaperCodeTweet Abstract The family of Salesforce CodeGen models is growing with CodeGen2.5 – a small, but mighty model! While there has been a recent trend…
TLDR We trained a series of 7B LLMs named XGen-7B with standard dense attention on up to 8K sequence length for up to 1.5T tokens. We also fine tune the models on public-domain…
