Pen and Paper Exercises in Machine Learning

michaelgutmann/ml-pen-and-paper-exercises 27 Jun 2022

This is a collection of (mostly) pen-and-paper exercises in machine learning.

Variational Inference

469
3.80 stars / hour

Multi-Graph Fusion Networks for Urban Region Embedding

wushangbin/mgfn 24 Jan 2022

Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks.

Crime Prediction

202
1.02 stars / hour

ProGen2: Exploring the Boundaries of Protein Language Models

salesforce/progen 27 Jun 2022

Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial intelligence-driven protein design.

67
0.75 stars / hour

Denoised MDPs: Learning World Models Better Than the World Itself

facebookresearch/denoised_mdp 30 Jun 2022

The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence.

Representation Learning

42
0.71 stars / hour

Ivy: Templated Deep Learning for Inter-Framework Portability

ivy-dl/ivy 4 Feb 2021

We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks.

2,958
0.67 stars / hour

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

lucidrains/parti-pytorch 22 Jun 2022

We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge.

Machine Translation Text to image generation +1

251
0.64 stars / hour

EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

tjiiv-cprg/epro-pnp CVPR 2022

The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution.

3D Object Detection 6D Pose Estimation using RGB +2

570
0.62 stars / hour

BokehMe: When Neural Rendering Meets Classical Rendering

juewenpeng/bokehme CVPR 2022

Based on this formulation, we implement the classical renderer by a scattering-based method and propose a two-stage neural renderer to fix the erroneous areas from the classical renderer.

Neural Rendering

73
0.58 stars / hour

Zero-Shot Text-to-Image Generation

borisdayma/dalle-mini 24 Feb 2021

Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset.

Ranked #12 on Text-to-Image Generation on COCO (using extra training data)

Text to image generation Zero-Shot Text-to-Image Generation

10,772
0.49 stars / hour

LViT: Language meets Vision Transformer in Medical Image Segmentation

huanglizi/lvit 29 Jun 2022

In our model, medical text annotation is introduced to compensate for the quality deficiency in image data.

Medical Image Segmentation Semantic Segmentation

18
0.49 stars / hour