Our paper, ORPO: Monolithic Preference Optimization without Reference Model with Noah Lee, is uploaded to Arxiv! Our best models, 🤗 Mistral-ORPO-$\alpha$ (7B) and 🤗 Mistral-ORPO-$\beta$ (7B), surpa...

Our paper, Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy is accepted to the Findings of EMNLP 2023!   Abstract We address an important gap in...

Our paper, MARL-Based Dual Reward Model on Segmented Actions for Multiple Mobile Robots in Automated Warehouse Environment is accepted to the Applied Science!   Abstract The simple and labor-int...