YOLOX: Exceeding YOLO Series in 2021

Megvii-BaseDetection/YOLOX 18 Jul 2021

In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.

2D Object Detection Autonomous Driving

1,728
8.58 stars / hour

Highly accurate protein structure prediction with AlphaFold

deepmind/alphafold Nature 2021

Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics.

Protein Folding Protein Structure Prediction

5,149
3.38 stars / hour

CycleMLP: A MLP-like Architecture for Dense Prediction

ShoufaChen/CycleMLP 21 Jul 2021

We build a family of models that surpass existing MLPs and achieve a comparable accuracy (83. 2%) on ImageNet-1K classification compared to the state-of-the-art Transformer such as Swin Transformer (83. 3%) but using fewer parameters and FLOPs.

Image Classification Instance Segmentation +2

62
1.58 stars / hour

Deduplicating Training Data Makes Language Models Better

google-research/deduplicate-text-datasets 14 Jul 2021

As a result, over 1% of the unprompted output of language models trained on these datasets is copied verbatim from the training data.

Language Modelling

96
0.65 stars / hour

Wizard of Wikipedia: Knowledge-Powered Conversational agents

facebookresearch/ParlAI ICLR 2019

In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date.

Dialogue Generation

7,974
0.54 stars / hour

Controlling Style in Generated Dialogue

facebookresearch/ParlAI 22 Sep 2020

Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters.

Dialogue Generation

7,975
0.52 stars / hour

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases

facebookresearch/convit 19 Mar 2021

We initialise the GPSA layers to mimic the locality of convolutional layers, then give each attention head the freedom to escape locality by adjusting a gating parameter regulating the attention paid to position versus content information.

Image Classification

233
0.50 stars / hour

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

kwai/DouZero 11 Jun 2021

Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents.

Game of Poker Multi-agent Reinforcement Learning

1,745
0.50 stars / hour

Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation

google/brax 24 Jun 2021

We present Brax, an open source library for rigid body simulation with a focus on performance and parallelism on accelerators, written in JAX.

OpenAI Gym

571
0.47 stars / hour

unilm

microsoft/unilm 15 Jun 2021

UniLM AI - Unified "Language" Model Pre-training across Tasks, Languages, and Modalities

Self-Supervised Image Classification Semantic Segmentation

2,413
0.47 stars / hour