Browsing: Research

We introduce Anthology, a method for conditioning LLMs to representative, consistent, and diverse virtual personas by generating and utilizing naturalistic…

Training Diffusion Models with Reinforcement Learning We deployed 100 reinforcement learning (RL)-controlled cars into rush-hour highway traffic to smooth congestion…

Efficient and grounded models: Contributing to AI Mode in Search As LLMs grow larger and demand increases, our ability to…

PLAID is a multimodal generative model that simultaneously generates protein 1D sequence and 3D structure, by learning the latent space…