Blogs

2026

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

Shayan Talaei*, Abhinav Chinta*, Devvrit Khatri, Amin Karbasi, Azalia Mirhoseini, Amin Saberi

Conference on Language Modeling, 2026

Paper · Website · Codebase

Toward Better HIP Kernel Generation for AMD GPUs: Synthetic Data, Multi-Agent Search, and Reinforcement Learning

Laasya Konidala*, Natalia Pahlavan*, Annmaria Antony*, Simon Guo, Azalia Mirhoseini

2026

Technical Talk at AMD AI Dev Day · Synthetic Data Codebase · Kernel Database

Decentralized Multi-Agent Systems with Shared Context

Yuzhen Mao, Azalia Mirhoseini

2026

Paper · Codebase · Project Page

LLM-as-a-Verifier: A General-Purpose Verification Framework

Jacky Kwok, Shulu Li, Pranav Atreya, Yuejiang Liu, Marco Pavone, Ion Stoica, Azalia Mirhoseini

2026

Blog · Codebase

TRACE: Capability-Targeted Agentic Training

Hangoo Kang*, Tarun Suresh*, Jon Saad-Falcon, Azalia Mirhoseini

2026

Codebase · Paper

OpenJarvis: Personal AI, On Personal Devices

Jon Saad-Falcon*, Avanika Narayan*, John Hennessy, Christopher Ré, Azalia Mirhoseini

2026

Paper · GitHub · Docs

Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment

Jacky Kwok*, Xilun Zhang*, Mengdi Xu, Yuejiang Liu, Azalia Mirhoseini, Chelsea Finn, Marco Pavone

Preprint, 2026

Paper · Codebase · Models

2025

Intelligence Per Watt: A Study of Local Intelligence Efficiency

Jon Saad-Falcon*, Avanika Narayan*, Hakki Orhun Akengin, J. Wes Griffin, Herumb Shandilya, Adrian Gamarra Lafuente, Medhya Goel, Rebecca Joseph, Shlok Natarajan, Etash Kumar Guha, Shang Zhu, Ben Athiwaratkun, John Hennessy, Azalia Mirhoseini, Christopher Ré

Preprint, 2025

Paper · Codebase

KernelBench v0.1

Natalia Kokoromyti, Sokserey Sun, Anne Ouyang, Azalia Mirhoseini

2025

Weaver: Shrinking the Generation-Verification Gap with Weak Verifiers

Jon Saad-Falcon*, E. Kelly Buchanan*, Mayee F. Chen*, Tzu-Heng Huang, Brendan McLaughlin, Tanvir Bhathal, Shang Zhu, Ben Athiwaratkun, Frederic Sala, Scott Linderman, Azalia Mirhoseini, Christopher Ré

Preprint, 2025

Paper · Codebase · Datasets and Models

RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models

Jacky Kwok, Christopher Agia, Rohan Sinha, Matt Foutter, Shulu Li, Ion Stoica, Azalia Mirhoseini, Marco Pavone

Preprint, 2025

Paper · Codebase · Datasets and Models · Serving Engine

Tokasaurus: An LLM Inference Engine for High-Throughput Workloads

Jordan Juravsky, Ayush Chakravarthy, Ryan Ehrlich, Sabri Eyuboglu, Bradley Brown, Joseph Shetaye, Christopher Ré, Azalia Mirhoseini

2025

Surprisingly Fast AI-Generated Kernels We Didn’t Mean to Publish (Yet)

Anne Ouyang, Percy Liang, Azalia Mirhoseini

2025

CodeMonkeys: Monkey SWE, Monkey Do

Ryan Ehrlich*, Bradley Brown*, Jordan Juravsky*, Ronald Clark, Christopher Ré, Azalia Mirhoseini

2025

Paper · CodeMonkeys Codebase · Trajectories · Codebase Content Dataset

2024

KernelBench: Can LLMs Write GPU Kernels?

Anne Ouyang*, Simon Guo*, Azalia Mirhoseini

2024

HF Dataset · Codebase · Leaderboard

Monkey Business: a Dataset of Large LLM Sample Collections for Math and Code Tasks

Bradley Brown*, Jordan Juravsky*, Ryan Ehrlich*, Ronald Clark, Quoc V. Le, Christopher Ré, Azalia Mirhoseini

2024

HF Dataset · Codebase · Paper

CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models

Je-Yong Lee*, Donghyun Lee*, Genghan Zhang, Mo Tiwari, Azalia Mirhoseini

Conference on Language Modeling, 2024

Blog Post · Code