@RicursiveAI on @nvidia 's slide at the #DAC2026# opening keynote. Thank you for the shoutout, Timothy Costa. Next up: our co-founder @Azaliamirh on the "New Minds, New Models" panel, 10:30am, Room 104A. Then find us at Booth #1049#.

How can we extract richer signals from AI Feedback? Introducing LLM-as-a-Verifier✨— a simple verification scaling framework that achieves SOTA on agentic benchmarks 🚀 The key idea: - Use fine-grained scoring granularity (e.g., 1-20 instead of the standard 1-5 scale) - Take the expectation over the full logprob distribution of score tokens - Scale repeated evaluation and criteria decomposition You can use these fine-grained signals for more effective test-time scaling, RL, and agent monitoring! It achieves SOTA across Terminal-Bench V2, SWE-Bench Verified, RoboRewardBench, and MedAgentBench 👑 Advised by @Azaliamirh @istoica05 @drmapavone @chelseabfinn 🧵👇

“TRACE: Capability-Targeted Agentic Training” got Spotlight @ ICML AIWILD 🎉 Beats direct RL, GEPA, & synthetic-agent data on SWE-Bench Verified and τ²-Bench. TRACE-Qwen3.6-27B tops GPT-5.2-Codex, GLM 5, & Claude 4.5 Sonnet on SWE-Bench. Co-led with @TarunSures41845. Thanks to @JonSaadFalcon and our advisor @Azaliamirh. Details below 👇

Suppose you're handed a fine-tuned LLM that secretly favors a certain entity. The bias goes completely undetected because it only surfaces on one specific unknown topic. So how do you catch a bias you can't search for? You amplify it. Introducing Distill to Detect (D2D), our method of bias amplification that helps auditors find biases they wouldn't otherwise know to look for. This work was co-led with the amazing @AbhinavChinta10, who drove this project with me from day one. Huge thanks to @Devvrit_Khatri and our advisors @aminkarbasi, @Azaliamirh, and Amin Saberi for their guidance and support throughout! 🙏 📄 Paper: 📝 Blog: 💻 Code: For more information, please see the thread below. 🧵

LLMs are good at CUDA because the internet is full of it. But a model that gives you highly optimized CUDA may still struggle to write compilable HIP. We built a synthetic data pipeline with multi-agent search and post-trained a 14B open-source model with SFT + GRPO RL, leading to substantially better HIP compilation + correctness rates on AMD MI350X GPUs.

OpenJarvis / @JonSaadFalcon, @Avanika15, @HazyResearch, @Azaliamirh (@Stanford) An open-source framework for local-first personal AI that runs agents on-device by default, calls the cloud only when necessary, and treats energy, cost, and latency as first-class metrics alongside accuracy.

Today, I’m excited to formally announce @mirendil with my amazing co-founders Harsh Mehta, Shayan Salehian, and Tara Rezaei! We’re fortunate to work with @a16z and @kleinerperkins, who led our seed round of $200M, followed by a major investment from NVIDIA, among others. Mirendil exists to accelerate science and technology, and through them, to help solve humanity's most pressing problems. Self-accelerating AI R&D is the most direct path to delivering on AI's broader promise, which is why we believe the most important application of AI is AI itself. Get this loop right, and it compounds. It fundamentally changes the rate of progress itself across all domains. We believe this capability should be democratized. It should be used to power all scientific efforts trying to innovate at the frontier. There are far more important problems—and broader ones—than any single lab can take on, so more groups should be able to pursue them. This pulls concentration of power away from a few labs: businesses and science labs can own their AI and infrastructure, keep their margins, and control their own destiny instead of ceding it all to a single AI lab. We’re a small team with a singular focus. Our founding team consists of 20 researchers and engineers from frontier institutions including Anthropic, xAI, Google DeepMind, and OpenAI, united by a passion for science and a drive to build the technologies that move it faster. If you want to build the system that builds systems, join us! @HarshMeh1a, @shayan_, @tararezaeikh

Happy to share that I’ve joined Ricursive Intelligence (@RicursiveAI) as a Student Researcher for the summer. Grateful to @annadgoldie and @Azaliamirh for the opportunity, and excited to work on ambitious projects with a great team.

A new Stanford framework called a decentralized language model, or DeLM, is built on the premise that #AI# agents can coordinate directly, without routing every update through a central controller. #ArtificialIntelligence# #GenerativeAI#