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.

0.37 stars / hour

Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces

dome272/paella 14 Nov 2022

Conditional text-to-image generation has seen countless recent improvements in terms of quality, diversity and fidelity.

Conditional Image Generation Denoising +2

0.37 stars / hour

Generate rather than Retrieve: Large Language Models are Strong Context Generators

wyu97/GenRead 21 Sep 2022

A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first retrieves a handful of relevant contextual documents from an external corpus such as Wikipedia and then predicts an answer conditioned on the retrieved documents.

Fact Checking Language Modelling +3

0.36 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

0.35 stars / hour

Fast Sampling of Diffusion Models with Exponential Integrator

shivamshrirao/diffusers 29 Apr 2022

Our goal is to develop a fast sampling method for DMs with a much less number of steps while retaining high sample quality.

0.34 stars / hour

Benchopt: Reproducible, efficient and collaborative optimization benchmarks

benchopt/benchopt 27 Jun 2022

Numerical validation is at the core of machine learning research as it allows to assess the actual impact of new methods, and to confirm the agreement between theory and practice.

Image Classification Stochastic Optimization

0.34 stars / hour
0.32 stars / hour

Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures

eladrich/latent-nerf 14 Nov 2022

This unique combination of text and shape guidance allows for increased control over the generation process.

Image Generation

0.32 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

0.30 stars / hour

DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models

luchengthu/dpm-solver 2 Nov 2022

The commonly-used fast sampler for guided sampling is DDIM, a first-order diffusion ODE solver that generally needs 100 to 250 steps for high-quality samples.

Text to image generation Text-to-Image Generation

0.30 stars / hour