MuJoCo: A physics engine for model-based control

deepmind/mujoco IEEE/RSJ IROS 2012

To facilitate optimal control applications and in particular sampling and finite differencing, the dynamics can be evaluated for different states and controls in parallel.

1,026
9.91 stars / hour

Non-deep Networks

imankgoyal/NonDeepNetworks 14 Oct 2021

This begs the question -- is it possible to build high-performing "non-deep" neural networks?

2D Object Detection Image Classification

94
3.01 stars / hour

Multitask Prompted Training Enables Zero-Shot Task Generalization

bigscience-workshop/promptsource 15 Oct 2021

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks.

Language Modelling

127
2.58 stars / hour

ADOP: Approximate Differentiable One-Pixel Point Rendering

darglein/ADOP 13 Oct 2021

The input are an initial estimate of the point cloud and the camera parameters.

Neural Rendering Novel View Synthesis

368
2.14 stars / hour

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

ifzhang/ByteTrack arXiv 2021

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos.

 Ranked #1 on Multi-Object Tracking on MOT17 (using extra training data)

Multi-Object Tracking

606
1.78 stars / hour

Graph Neural Networks with Learnable Structural and Positional Representations

vijaydwivedi75/gnn-lspe 15 Oct 2021

An approach to tackle this issue is to introduce Positional Encoding (PE) of nodes, and inject it into the input layer, like in Transformers.

Knowledge Graphs Recommendation Systems

50
1.68 stars / hour

Lenia and Expanded Universe

Chakazul/Lenia 7 May 2020

We report experimental extensions of Lenia, a continuous cellular automata family capable of producing lifelike self-organizing autonomous patterns.

Artificial Life

2,598
1.68 stars / hour

Alias-Free Generative Adversarial Networks

NVlabs/stylegan3 23 Jun 2021

We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner.

Image Generation

2,475
1.67 stars / hour

SaLinA: Sequential Learning of Agents

facebookresearch/salina 15 Oct 2021

SaLinA is a simple library that makes implementing complex sequential learning models easy, including reinforcement learning algorithms.

56
1.67 stars / hour

Resolution-robust Large Mask Inpainting with Fourier Convolutions

saic-mdal/lama 15 Sep 2021

We find that one of the main reasons for that is the lack of an effective receptive field in both the inpainting network and the loss function.

Image Inpainting LAMA

312
1.09 stars / hour