Ask Me Anything: A simple strategy for prompting language models

hazyresearch/ama_prompting 5 Oct 2022

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.

Coreference Resolution Natural Language Inference +2

3.72 stars / hour

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

gcorso/diffdock 4 Oct 2022

Predicting the binding structure of a small molecule ligand to a protein -- a task known as molecular docking -- is critical to drug design.

Blind Docking

2.18 stars / hour

Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

allenai/rl4lms 3 Oct 2022

To help answer this, we first introduce an open-source modular library, RL4LMs (Reinforcement Learning for Language Models), for optimizing language generators with RL.

Decision Making Policy Gradient Methods +2

1.66 stars / hour

clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIP

justinpinkney/clip2latent 5 Oct 2022

We introduce a new method to efficiently create text-to-image models from a pre-trained CLIP and StyleGAN.


1.49 stars / hour

VICRegL: Self-Supervised Learning of Local Visual Features

facebookresearch/vicregl 4 Oct 2022

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.

Self-Supervised Learning

1.42 stars / hour

Human Motion Diffusion Model

guytevet/motion-diffusion-model 29 Sep 2022

In this paper, we introduce Motion Diffusion Model (MDM), a carefully adapted classifier-free diffusion-based generative model for the human motion domain.

Motion Synthesis

1.25 stars / hour

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

XavierXiao/Dreambooth-Stable-Diffusion 25 Aug 2022

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.

Image Generation

1.19 stars / hour

VToonify: Controllable High-Resolution Portrait Video Style Transfer

williamyang1991/vtoonify 22 Sep 2022

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.

Face Alignment Style Transfer +1

1.05 stars / hour

Protein structure generation via folding diffusion

microsoft/foldingdiff 30 Sep 2022

The ability to computationally generate novel yet physically foldable protein structures could lead to new biological discoveries and new treatments targeting yet incurable diseases.

Denoising Protein Structure Prediction

1.02 stars / hour

Min-Max Similarity: A Contrastive Semi-Supervised Deep Learning Network for Surgical Tools Segmentation

angeloucn/min_max_similarity 29 Mar 2022

To address this issue, we proposed a semi-supervised segmentation network based on contrastive learning.

Contrastive Learning Video Segmentation +1

0.98 stars / hour