Salman Abdullah

Looking for a RAG system that navigates between granular details and the big picture? We’re excited to introduce RAPTOR, a tree-based retrieval approach that sets a new SoTA on 3 benchmarks #ICLR2024 w/@salmanabdullah_ , @aditituli_, @shubhkhanna__, @annadgoldie & @chrmanning at @stanfordNLP arxiv.org/abs/2401.18059 🧵

Exploration is fundamental to RL. Yet policy gradient methods often collapse: during training they fail to explore broadly, and converge into narrow, easily exploitable behaviors. The result is poor generalization, limited gains from test-time scaling, and brittleness on tasks where strategic exploration is necessary. We introduce a framework for training a policy over sets of generations and use it to induce exploration. Work with @ifdita_hasan (co-lead), @ellenjxu_ , @chelseabfinn and @DorsaSadigh at Stanford 🧵

Talked AI with youngsters from the Indian StartUp world. It was a memorable and insightful interaction, in which they shared their vision and work on how India is transforming the world of AI. It is commendable how these StartUps are working on diverse fields such as e-commerce, marketing, engineering simulations, material research, healthcare, medical research and more. pib.gov.in/PressReleseDet…

Introducing 🔥Optimas🔥: The first unified framework to optimize compound AI systems composed of multiple components like trainable/API-based LLMs, tools, model routers, and traditional ML models! 🌐 👉🏻 optimas.stanford.edu 🌟 Why Optimas? AI systems today combine diverse elements—prompts, model parameters, hyperparameters, and model router. Optimizing the entire system effectively is tough! Optimas tackles this with an intuitive strategy: Globally Aligned Local Rewards (LRFs), ensuring each component's optimization directly boosts overall system performance! 📈 Impressive Results: Tested rigorously on 5 real-world compound AI tasks: Product Recommendation, Medical QA, Complex Retrieval, Multi-hop QA, and Code Generation. 🤩 Delivers an impressive average boost of 11.92% over top baselines (e.g., LLMSelector, TextGrad, DSPy). 🔧 Here's the magic behind Optimas: ① Assigns each component a Local Reward Function (LRF). ② Aligns these LRFs with global objectives, enabling independent yet coordinated optimizations. ③ Adaptively updates LRFs for efficient, coherent improvements across diverse configurations. 💡 Compatible with popular agentic frameworks Easily optimize your own systems! Integrates with popular agentic frameworks like @DSPyOSS, @crewAIInc, @pyautogen, TextGrad, and OpenAI Agent SDK @OpenAIDevs! Proudly developed by an outstanding collaboration between @StanfordAILab, @AmazonScience, and more! Grateful to work with team @parthsarthi03, Shiyu, Aaron, @krypticmouse, @Diyi_Yang, @james_y_zou, @jure etc.! Check out more! 📄 Paper: arxiv.org/abs/2507.03041 💻 Code: github.com/snap-stanford/… (to be open-sourced soon!) #CompoundAISystem #LLM #Optimization #MachineLearning

Excited to announce MIRIAD — a large-scale dataset of 5,821,948 medical question-answer pairs, each rephrased from passages in the medical literature. Great collab with @QueyJ, @salmanabdullah_, @samarthrawal, @cyrilzakka, @SophieOstmeier, Maximilian Purk, @edreisMD, @EricTopol & @jure! Page: med-miriad.github.io Dataset: huggingface.co/miriad Preprint: arxiv.org/abs/2506.06091 Code: github.com/eth-medical-ai… Demo: med-miriad.github.io/demo [1/n]