Prompting is a brittle process wherein small modifications to the prompt can cause large variations in the model predictions, and therefore significant effort is dedicated towards designing a painstakingly "perfect prompt" for a task.
Ranked #2 on Question Answering on Story Cloze Test
Predicting the binding structure of a small molecule ligand to a protein -- a task known as molecular docking -- is critical to drug design.
Ranked #1 on Blind Docking on PDBBind
To help answer this, we first introduce an open-source modular library, RL4LMs (Reinforcement Learning for Language Models), for optimizing language generators with RL.
We introduce a new method to efficiently create text-to-image models from a pre-trained CLIP and StyleGAN.
Most recent self-supervised methods for learning image representations focus on either producing a global feature with invariance properties, or producing a set of local features.
Once the subject is embedded in the output domain of the model, the unique identifier can then be used to synthesize fully-novel photorealistic images of the subject contextualized in different scenes.
Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency.
The ability to computationally generate novel yet physically foldable protein structures could lead to new biological discoveries and new treatments targeting yet incurable diseases.