Amazing work by Camilo Ruiz combining knowledge graphs and high dimensional deep learning on tabular data!

Thrilled that a paper from my PhD, "Faster Maximum Inner Product Search in High Dimensions" has been accepted to ICML 2024! In the paper, we accelerate state-of-the-art for the Maximum Inner Product Search (MIPS) problem. MIPS is a core subroutine in systems like recommendation

Thrilled to announce that I joined OpenAI a few months ago! I'm back in SF and working out of the headquarters. A special thank-you to my management chain and the many friends that made this happen. If you and I have worked together in the past and you'd like a referral, please

I'll be at ICML in Vienna next week -- come say hi!

We are hiring a postdoc to work on research at the intersection of LLMs, reasoning, and data! For more info, please take a look here: scalingintelligence.stanford.edu The position is joint between my lab and Prof. Saberi's lab at Stanford!

Very excited to introduce Archon, a framework for LLM inference-time architecture search! Paper: arxiv.org/abs/2409.15254 Code: github.com/ScalingIntelli… Project: scalingintelligence.stanford.edu/pubs/archon/

🚨 Multi-agent systems are no longer safe from prompt injection! In our paper, we introduce Prompt Infection—an infectious prompt injection attack that spreads like a virus across LLM agents, turning your multi-agent system into a network of compromised agents. TL;DR: 1. One

Announcing LeanAgent: the first life-long learning agent for formal theorem proving in Lean. LLMs have been integrated with interactive proof assistants like Lean for theorem proving with 100% accuracy. So far, these LLMs are static, cannot learn new knowledge online, and

AI as AI compiler? Very excited to release KernelBench, a new code generation benchmark for evaluating models' ability to generate correct and efficient CUDA kernels. KernelBench has 4 levels: Level 1 (100 tasks): Single-kernel operators (e.g. matmuls) Level 2 (100 tasks):

We are excited to share our #ICLR2025 paper on LeanAgent: the first lifelong learning agent for formal theorem proving in Lean. LLMs have been integrated with interactive proof assistants like Lean for theorem proving with 100% accuracy. So far, these LLMs cannot continuously

Excited to release SWiRL: A synthetic data generation and multi-step RL approach for reasoning and tool use! With SWiRL, the model’s capability generalizes to new tasks and tools. For example, a model trained to use a retrieval tool to solve multi-hop knowledge-intensive

1/ 🔥 AI agents are reaching a breakthrough moment in cybersecurity. In our latest work: 🔓 CyberGym: AI agents discovered 15 zero-days in major open-source projects 💰 BountyBench: AI agents solved real-world bug bounty tasks worth tens of thousands of dollars 🤖

Amazing work by my long-time collaborators and close friends Ryan Kang and Jeyong Lee!!

An awesome event with an incredible lineup of speakers! Check out the recordings here: rdi.berkeley.edu/events/agentic…

I have achieved full skong

Introducing intelligence per watt, and predicting a distribution shift from cloud to edge inference!