EvoTune
Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
- 146
- Python
- MIT
- 12 mo ago
CLAIRE-Labo
Caglar Gulcehre Laboratory for AI Research
Built from CLAIRE-Labo's public GitHub profile, Switzerland. Not on Take My Repo yet, so there are no posts or updates here.
Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
A template for starting reproducible Python machine-learning projects with hardware acceleration. Find an example at https://github.com/CLAIRE-Labo/no-representation-no-trust
Codebase to fully reproduce the results of "No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO" (Moalla et al. 2024). Uses TorchRL and provides extensive tools for studying representation dynamics in policy optimization.
Official codebase for "Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions" (Matrenok et al. 2025).
Official code for the NeurIPS25 paper "RAT: Bridging RNN Efficiencyand Attention Accuracy in Language Modeling" (https://arxiv.org/abs/2507.04416))
The official code of "Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers"
Supplementary code for "In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning"