2022 · Chips
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
FlashAttention reorganizes attention computation to reduce costly reads and writes between GPU memory levels.
Paper & contextChristopher Ré
Making learning systems more efficient and usable.
Ré studies the systems, data, and algorithms that make machine learning practical. These papers connect efficient model execution with language-model evaluation and data-centric development, treating system design as part of the learning problem.
Selected work
10 papers
2022 · Language models
Holistic Evaluation of Language Models
Selected research in language models, ai evaluation. Read the full paper, including the methods, experiments, and reported results.
Paper & context2021 · Computer vision
On the Opportunities and Risks of Foundation Models
Selected research in computer vision, language models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Efficient AI
Predict before you train: Scaling Laws for particle physics foundation models
Selected research in efficient ai. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Efficient AI
MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers
Selected research in efficient ai. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Efficient AI
OpenJarvis: Personal AI, On Personal Devices
Selected research in efficient ai. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Efficient AI
Olmix: A Framework for Data Mixing Throughout LM Development
Selected research in efficient ai. Read the full paper, including the methods, experiments, and reported results.
Paper & context2025 · Efficient AI
An Information Theoretic Perspective on Agentic System Design
Selected research in efficient ai. Read the full paper, including the methods, experiments, and reported results.
Paper & context2025 · Efficient AI
ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels
Selected research in efficient ai. Read the full paper, including the methods, experiments, and reported results.
Paper & context2025 · Efficient AI
HipKittens: Fast and Furious AMD Kernels
Selected research in efficient ai. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAn independent editorial profile. Inclusion does not imply Council membership or endorsement. Research is collaborative; coauthorship does not imply sole credit.
Selection & sources