Machine Learning Professor @ Caltech
Professor of Computing and Mathematical Sciences at Caltech.
Research Interests: Machine Learning and Artificial Intelligence.
Industry Advising: Asari AI, Cainex, Latitude AI, Lila Sciences, and Tera AI.
ICLR Leadership: Member of ICLR Board. General Chair of ICLR 2025. Senior Program Chair of ICLR 2024.
Data & Evaluation. Create new data engines. Create benchmarks that are formally verified. Unify scientific inverse problems into common frameworks.
Models & Architecture. Create new effective representations, such as for time series.
Inference & Search. Develop Bayesian inference methods using diffusion priors. Develop advanced LLM reasoning methods such as dynamic tree decomposition and self-training. Develop abstractions to simplify agent programming.
We introduce a systematic evaluation framework for agentic code optimization and use it to study three production-level biomedical imaging pipelines. We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions. Our analysis reveals that common, complex agent architectures are not universally beneficial, leading to a practical roadmap for agent design.
We present Steer3D: a method to add text steerability to pretrained image-to-3D generative models. Steer3D adapts the ControlNet architecture to 3D generation. Training only on 100k-scale synthetic data generated by our data engine, Steer3D and can perform diverse edits, and even generalize to objects in iPhone photos or online images.
We developed CellSAM, a universal model for cell segmentation that generalizes across diverse cellular imaging data.
We introduce a new approach to agent programming that disentangles these core agent logic from the inference time strategy.
We present a method for dynamically decomposing tree-search inference with LLMs, leading to significant improvements in accuracy/cost trade-off.
We had six members depart the group during the 2024-2025 Academic Year.
I am honored to receive the mentoring award from the Grad Student Advisory Board of Caltech EAS.
I an co-organizing a workshop at COLM 2025 on Language Modeling for Scientific Discovery.