From the lab
How Stanford researchers are using Marlowe — from brain-scale neural networks and genomic foundation models to autonomous systems and beyond.
Counterfactual World Modeling: Training Brain-Scale Neural Networks
Validated 80B-parameter brain-inspired neural network training on Marlowe in a February 2026 proof-of-concept. Now training PSI2-30B — a 30-billion...
Read full story →
The Enigma Project: First Foundation Model and Digital Twin of the Brain
Trained the first foundation model of mammalian visual cortex on Marlowe — a 2B-parameter multimodal transformer on recordings from 3 million neuro...
Read full story →
AI Virtual Cell: Genomic Foundation Models at Frontier Scale
Building the molecular foundation of the AI Virtual Cell — novel reasoning architectures designed for biological data modalities (DNA, RNA, protein...
World Models for Cancer Biology
Published a vision-language foundation model in Nature (January 2025) and AI-enabled virtual spatial proteomics in Nature Medicine (January 2026) f...
Vision-Language Foundation Models for Radiology
We are building a vision-language foundation model for medical image interpretation, trained on Stanford's 2 petabytes of radiology data. Our first...
Video World Models for 3D Scene Understanding and Generation
Fine-tuning billion-parameter video diffusion models on Marlowe for spatially aware scene understanding and generation. Two active projects: real-t...
Beyond Evo 2: Next-Generation Biological Models
Creators of Evo 2, the state-of-the-art DNA language model published in Nature, now developing next-generation biological models on Marlowe to addr...
4D Scene Understanding: AI for Dynamic Real-World Environments
Two active projects in 4D scene understanding on Marlowe. ReScene4D introduces temporally consistent instance segmentation from sparse 3D scans — a...
AI Agents for Biomedical Discovery: Self-Improving LLMs with Scientific Tools
Developing algorithms that enable large language models to self-improve and learn to use scientific tools like AlphaFold and biomedical databases t...
Parallel Chain-of-Thought: Reducing LLM Reasoning Latency via RL
Teaching reasoning LLMs to parallelize their long chains of thought using reinforcement learning — spawning parallel workers that investigate diffe...
Efficient AI Computing: From Model Compression to Edge-Deployable Video Generation
Extending BlockDialect (ICML 2025), their fine-grained mixed-format quantization method, from LLMs to video diffusion transformers — enabling real-...
Physics-Guided AlphaFold3: Reinforcement Learning for Drug Discovery
Training AlphaFold3 with reinforcement learning and physics-based Rosetta scoring on Marlowe to produce physically realistic molecular structures f...
Time Machine: Time-Aware Pretrained LLMs for Finance and Economics
Pioneering time-aware LLMs that eliminate look-ahead bias — a fundamental flaw making current models unreliable for finance, economics, and policy ...
Personal and Efficient Local AI
OpenJarvis is an open-source framework for personal AI that runs entirely on personal devices, keeping user data local and calling the cloud only w...
Frontiers of AI Scaling: Synthetic Data and Test-Time Reasoning
As the finite pool of internet text that powered a decade of AI scaling runs dry, Candès's group uses Marlowe to chart the next frontiers — generat...