Princeton Natural Language Processing

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

princeton-nlp

SimPO: Simple Preference Optimization with a Reference-Free Reward

princeton-nlp

[NeurIPS 2024] CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs

princeton-nlp