Bo Pang is a Lead Research Scientist at Salesforce AI Research. He has been working on LLM pre-training and post-training, and more recently, reasoning model training and LLM agents.
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…
xGen-small is an enterprise-ready compact LM that combines domain-focused data-curation, scalable pre-training, length-extension, instruction fine-tuning, and reinforcement-learning to deliver Enterprise AI with long-context performance at predictable, low cost.
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…
