My research interests focus on machine learning systems, AI safety, and mechanistic understanding of modern foundation models, particularly around hallucination
hallbayes. Python
1.7kntkmirror. Python
347mezzanine. Python
145ITO. Python
65teta. TeX
36factuality-slice. Python
30openbook. TeX
22berry. Python
15medium. Jupyter Notebook
9bayesian-flashcards. A modern, extensible, and research-backed flashcard app designed for optimal learning, focus, and memory—especially for users with ADHD and anyone who wants smarter, science-based study sessions.
6aecf. Code accompanying Adaptive Entropy-Gated Contrastive Fusion: Robust Multimodal Learning under Missing Modalities
5procedural_chlon2026. Supporting experiments
3triton-blackwell. Python
2bgz.
1optimistix. Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
1cvhack. Python
1pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration
1optax. Optax is a gradient processing and optimization library for JAX.
1rfcs. PyTorch RFCs (experimental)
1transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
1leochlon.github.io. JavaScript
1watermark-edfl-toolkit. Information-theoretic robustness certification toolkit for logits-based text watermarks (SynthID, KGW-family).
1