🚀 First step to unlocking Generalist Robots! Introducing 🤖LAPA🤖, a new SOTA open-sourced 7B VLA pretrained without using action labels. 💪SOTA VLA trained with Open X (outperforming OpenVLA on cross and multi embodiment) 😯LAPA enables learning from human videos, unlocking

🚀 Excited to co-lead this paper with Hyeonbin Hwang ! 🧠 Our preliminary work demonstrates adapting language models for sentence-level reasoning—both at latent and language levels. 🔍 Plus, we introduce SentenceLens to visualize hidden states at the sentence level. Check it out! 👀

[1/6] Ever wondered why Direct Preference Optimization is so effective for aligning LLMs? 🤔 Our new paper dives deep into the theory behind DPO's success, through the lens of information gain. Paper: "Differential Information: An Information-Theoretic Perspective on Preference