-
RaySearch Laboratories
- Stockholm
- @neuraloverflow
🔮 Future ideas
[CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation
New flexible and efficient image generation framework that sets new SOTA on FFHQ-256 with FID 2.05, 2022
On the "steerability" of generative adversarial networks
Unofficial implementation of the DragGAN paper
Training PyTorch models with differential privacy
🔮 Fast and full-featured autocomplete library
[CVPR 2022] Unsupervised Image-to-Image Translation with Generative Prior
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models, arxiv 2023 / CVPR 2024
Dopamine: Differentially Private Federated Learning on Medical Data (AAAI - PPAI)
Type-safe, K-sortable, globally unique identifier inspired by Stripe IDs
A PyTorch Lightning solution to training OpenAI's CLIP from scratch.
DreamerV3 implementation of Curious Replay, a method for prioritizing experience replay that is tailored to model-based reinforcement learning agents.
Convert any website to editable Figma designs
Unoffical implement for [StyleDrop](https://arxiv.org/abs/2306.00983)
📊 A simple command-line utility for querying and monitoring GPU status
Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.
Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to Retool and Temporal.
Personal CRM. Remember everything about your friends, family and business relationships.
Open source application for creating free invoices and receipts
Quickly design beautiful screenshots and open graph images
🕵️♂️ All-in-one OSINT tool for analysing any website
A service template for asynchronous machine learning model training
Muzic: Music Understanding and Generation with Artificial Intelligence
My best practice of training large dataset using PyTorch.
⏰ AI conference deadline countdowns
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
A Library for Advanced Deep Time Series Models.
pix2tex: Using a ViT to convert images of equations into LaTeX code.