Leon Chlon
I'm a machine-learning researcher working on AI safety, LLM reliability, and the mechanistic understanding of foundation models. My recent work asks why language models hallucinate, and how structured inductive biases, symmetry-aware learning, and a Bayesian perspective can make them more reliable and interpretable.
I also work on world models, multimodal learning, and physics-informed ML, where principled modeling bridges theory with scalable systems. Currently Visiting Fellow at the University of Oxford (Torr Vision Group), and founder of Hassana Labs, a research organization opening doors in AI for researchers from marginalized communities. I'm writing an open-source book, Information Geometry for Generative Models, released free with donations going to Lebanese refugees.
News
- 2026 Predictable Compression Failures: Why Language Models Actually Hallucinate accepted at ICML 2026.
- 2026 Won $300K in backing from Microsoft, Google, and NVIDIA to fund an AI-research sabbatical at Oxford's Torr Vision Group.
- 2026 HallBayes featured at NVIDIA GTC 2026; integrated into PyTorch Geometric (1.6k★, 150+ forks).
- 2025 Co-designed CUDA INT4 kernels with Prof. Omri Weinstein (Hebrew University of Jerusalem) and Unsloth; cut quantization penalty by ~9% on GPTQ/GGUF (Qwen3.5).
- 2025 HP & NVIDIA-sponsored Triton kernels for Blackwell GB10 (sm_121); 6.1× over PyTorch baselines.
- 2025 Released Mezzanine, a post-training toolkit adopted by DeepMind, CERN, DAMTP, and CRUKCI; powered the first pixel-free I-JEPA for robotics.
Selected publications
-
Predictable Compression Failures: Why Language Models Actually Hallucinate
-
LLMs are Bayesian, in Expectation, not in Realization
-
Attention Deficits in Language Models: Causal Explanations for Procedural Hallucinations
Open source
- hallbayes ★ 1,664 Model-agnostic post-training to suppress LLM hallucinations. Integrated into PyTorch Geometric. Featured at NVIDIA GTC 2026.
- mezzanine ★ 143 Post-training toolkit. Adopted by DeepMind, CERN, DAMTP, and CRUKCI. First pixel-free I-JEPA for robotics; 2.1× retrieval-rank improvement on LeRobot ALOHA.
- triton-blackwell ★ 2 Fused Triton transformer kernels for Blackwell GB10 (sm_121); 6.1× over PyTorch baselines.
- berry ★ 14 Information-budget MCP server for hallucination detection in agent workflows.
Other public research code: ITO (★65) · teta (★33) · factuality-slice (★31) · aecf (★4).
Core contributions to DeepMind Optax and HuggingFace; 4× speedup in SAM image processing. EWOR Fellowship (0.1% acceptance rate).
Selected work
- University of Oxford · Visiting Fellow 2025–present Torr Vision Group. Building HallBayes, Mezzanine, and Triton kernels for Blackwell GB10.
- Apple · Content Ranking 2023–2025 Production MMoE on TensorFlow + ONNX Runtime; 43% p50-latency reduction on workloads serving 50M+ requests/day.
- TikTok · Post-training, Ranking 2023–2025 Bayesian-optimised MMoE retraining across a 500M+ DAU ranking system; double-digit gains in cross-platform sharing.
- World Bank Group · Post-training 2023–2025 Fine-tuned LLaMA-2 70B LoRa adapters across 300k socioeconomic indicators; reduced forecast error by 35% sMAPE; immediate adoption across 15 cross-country teams.
- Tailor Bio · Founding AI Engineer (0→1) 2022–2023 Cambridge spinout. Drug-discovery stack on AWS (PyTorch, RDKit, Neo4j); custom sparse mat-mul + gradient checkpointing. 3× throughput; 3 lead compounds validated for Series B.
- Uber / Careem · Lead ML Engineer, Dynamic Pricing 2022 Marketplace pricing for 100M+ users via algorithmic game theory; 2.7× efficiency over legacy; $2M+ revenue impact.
- Meta · Senior Research Scientist, AI Safety 2020–2022 Bayesian RL for crash detection across Instagram / WhatsApp / Facebook; FAISS / HNSW vector embeddings improving hate-speech recall by 15% at billion-post scale.
- McKinsey & Company · Senior Data Scientist 2018–2020 Gradient-boosting credit-risk models for Tier-1 banks covering $100B+ exposures; Basel III / IFRS 9 strategies for C-suite at three major institutions.
Talks & writing
Education
- Massachusetts Institute of Technology 2018 Postdoctoral Researcher, Machine Learning
- University of Cambridge 2017 PhD, Machine Learning
- University of Cambridge 2014 MPhil, Theoretical Physics