- London, United Kingdom
- https://batjandra.github.io/
Stars
A synthetic reasoning benchmark for learning on temporal graphs.
Fast, secure, and practical Python sandbox designed specifically for safely executing code generated by LLMs
batjandra / ART
Forked from OpenPipe/ARTAgent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
A List of Papers on Theoretical Foundations of Graph Neural Networks
Source code for our AAAI paper "Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks".
Sample code for Further Graphics lectures, Cambridge University.
A curated list of cryptography papers, articles, tutorials and howtos.
A toolkit for making real world machine learning and data analysis applications in C++
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow