arnaudgardille's Projects
Generate comic panels using a LLM + SDXL. Powered by Hugging Face š¤
This is a workshop designed for Amazon Bedrock a foundational model service.
An annotated implementation of the Transformer paper.
Config files for my GitHub profile.
āØ Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com
Official community-driven Azure Machine Learning examples, tested with GitHub Actions.
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Carla simulator wrapped as a gym environment and usable by Stable Baselines
Bird-eye's view for CARLA simulator
Teaching a 2D car to drive using reinforcement learning
Code repository of the paper "CITRIS: Causal Identifiability from Temporal Intervened Sequences" and "iCITRIS: Causal Representation Learning for Instantaneous Temporal Effects"
A simple version of the game "Colt Express" implemented during my bachelor
Tools for correcting XML files of PDFs in Factur-X format
Benchmarking Multi-Agent Debate between Language Models for Truthfulness in Q&A.
Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
Decision Transformer JAX - Reproduction of 'Decision Transformer: Reinforcement Learning via Sequence Modeling' in JAX and Haiku
Deep functional residue identification
Project of automated power grid management during my bachelor
An extension of the PyMARL codebase that includes additional algorithms and environment support
Startup project: contains my MVP, which consists of an iOS app, as well as my business canva and my business plan.
Google Research
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577
An OpenAI gym wrapper for CARLA simulator
An algorithm to play strategy games in a recursive way using reinforcement learning
A minimalist environment for decision-making in autonomous driving
The objective is to produce color images given grayscale input image.
Code for experiments regarding importance sampling for training neural networks