- New York City, NY
- https://solimlegris.com/
- https://orcid.org/0009-0003-2334-7234
Highlights
- Pro
Stars
Data release for the Model Synthesis Architectures experiments that appear at CogSci 2025
This is the code repository for IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models.
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Solving ARC-AGI as an inpainting problem with Discrete Diffusion Models
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
NiceWebRL is a Python library for quickly making human subject experiments that leverage machine reinforcement learning environments.
This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"
$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).
Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase
Repository for the paper Stream of Search: Learning to Search in Language
Wu, C. M., Schulz, E., Speekenbrink, M., Nelson, J. D., & Meder, B. (2018). Generalization guides human exploration in vast decision spaces. Nature Human Behaviour. 2, 915–924. https://doi.org/10.1…
📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors
Tools for working with the Abstraction & Reasoning Corpus
neural sketch project, currently in generative regex, list transformation (deepcoder), and text editing (robustfill) domains
Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge
Tips and resources to prepare for Behavioral interviews.
Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
A probabilistic programming language for metacognitive modeling
Reverse Engineering the Abstraction and Reasoning Corpus
In which I put together my thoughts on the practice of data science.
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more