TorchScale: Transformers at Scale

microsoft/torchscale 23 Nov 2022

Large Transformers have achieved state-of-the-art performance across many tasks.

Language Modelling Machine Translation +1

766
2.68 stars / hour

Human-level play in the game of Diplomacy by combining language models with strategic reasoning

facebookresearch/diplomacy_cicero Science 2022

Despite much progress in training AI systems to imitate human language, building agents that use language to communicate intentionally with humans in interactive environments remains a major challenge.

687
2.38 stars / hour

Towards Robust Blind Face Restoration with Codebook Lookup Transformer

sczhou/codeformer 22 Jun 2022

In this paper, we demonstrate that a learned discrete codebook prior in a small proxy space largely reduces the uncertainty and ambiguity of restoration mapping by casting blind face restoration as a code prediction task, while providing rich visual atoms for generating high-quality faces.

Blind Face Restoration

1,500
0.76 stars / hour

SinDiffusion: Learning a Diffusion Model from a Single Natural Image

weilunwang/sindiffusion 22 Nov 2022

We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image.

Denoising Image Generation +1

107
0.71 stars / hour

MetaFormer Baselines for Vision

facebookresearch/xformers 24 Oct 2022

By simply applying depthwise separable convolutions as token mixer in the bottom stages and vanilla self-attention in the top stages, the resulting model CAFormer sets a new record on ImageNet-1K: it achieves an accuracy of 85. 5% at 224x224 resolution, under normal supervised training without external data or distillation.

Image Classification

1,704
0.69 stars / hour

LiT: Zero-Shot Transfer with Locked-image text Tuning

mlfoundations/open_clip CVPR 2022

This paper presents contrastive-tuning, a simple method employing contrastive training to align image and text models while still taking advantage of their pre-training.

Image Classification Retrieval +2

2,397
0.63 stars / hour

DiffusionDet: Diffusion Model for Object Detection

shoufachen/diffusiondet 17 Nov 2022

In inference, the model refines a set of randomly generated boxes to the output results in a progressive way.

Denoising object-detection +1

1,311
0.62 stars / hour

VeLO: Training Versatile Learned Optimizers by Scaling Up

google/learned_optimization 17 Nov 2022

While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers.

447
0.58 stars / hour

A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases

google/learned_optimization 22 Sep 2022

We apply the resulting learned optimizer to a variety of neural network training tasks, where it outperforms the current state of the art learned optimizer -- at matched optimizer computational overhead -- with regard to optimization performance and meta-training speed, and is capable of generalization to tasks far different from those it was meta-trained on.

Inductive Bias

447
0.54 stars / hour