Institution profile

California Institute of Technology

Academic institutionnorthamerica · us
Official website
Research library717linked papers
Opportunities0open roles
Selected work

Representative Papers

The Unpaid Toll: Quantifying the Public Health Impact of AI

Dec 09, 2024arXiv.org

The environmental health impacts and associated environmental injustice of AI’s full lifecycle—from semiconductor manufacturing to datacenter operations—remain poorly quantified. Method: We develop the first integrated AI health impact quantification framework, combining multi-source emission inventories, life cycle assessment, atmospheric transport modeling, health risk assessment, and spatial environmental justice statistics. Contribution/Results: Training Llama3.1 generates PM₂.₅ emissions equivalent to over 10,000 round-trip automobile journeys between Los Angeles and New York. Health burdens exhibit pronounced spatial heterogeneity—up to a 200-fold disparity across U.S. census tracts—disproportionately affecting marginalized communities. By 2030, AI-related datacenter operations in the U.S. are projected to incur annual health costs exceeding $20 billion. We propose mandatory disclosure standards for AI health externalities and a health-centered governance framework to advance equitable, sustainable AI development.

13 citations1 influentialRead paper

Fourier Continuation for Exact Derivative Computation in Physics-Informed Neural Operators

Nov 29, 2022arXiv.org

Physics-informed neural operators (PINO) suffer from Gibbs phenomena and high-order derivative inaccuracies when solving non-periodic, non-smooth PDEs, due to the inherent periodicity assumption of Fourier spectral methods. Method: This work systematically integrates Fourier continuation (FC) into the PINO architecture, proposing three FC-PINO variants. FC enables exact frequency-domain differentiation for non-periodic functions, eliminating gradient estimation bias and optimization failure caused by conventional zero- or symmetric-padding strategies. Contribution/Results: On a 1D blow-up problem, FC-PINO reduces PDE residuals by several orders of magnitude and—uniquely among neural operators—achieves accurate modeling of third-order derivatives for non-smooth solutions. It significantly enhances training stability and generalization accuracy. This establishes a new paradigm for neural operator modeling of non-periodic physical systems.

13 citationsRead paper

An Addendum to NeBula: Toward Extending Team CoSTAR’s Solution to Larger Scale Environments

Apr 18, 2025IEEE Transactions on Field Robotics

Autonomous collaborative exploration in ultra-large-scale, unstructured underground environments remains challenging due to severe communication constraints, navigation uncertainty, and lack of prior maps. Method: This work extends TEAM CoSTAR’s NeBula autonomy system with a full-stack enhancement framework integrating semantic-geometric joint mapping, distributed POMDP-based global planning under communication constraints, adaptive filtering for localization, Gaussian process–based probabilistic traversability modeling, edge-cloud cooperative communication protocols, and aerial-ground heterogeneous multi-agent task allocation. Contribution/Results: The framework achieves, for the first time, robust long-range mapping (>5 km²), sub-meter localization accuracy (<0.3 m), and decentralized collaborative decision-making in kilometer-scale underground spaces (e.g., limestone mines). Validated in the DARPA Subterranean Challenge and real-world mine deployments, it improves mission completion rate by 37%, significantly advancing scalability, robustness, and coordination in autonomous underground exploration.

6 citationsRead paper

Gibbs state preparation for commuting Hamiltonian: Mapping to classical Gibbs sampling

Oct 07, 2024arXiv.org

Efficient preparation of Gibbs states for commuting local Hamiltonians (CLHs)—particularly topologically ordered systems such as the toric code—at arbitrary nonzero temperatures, including the low-temperature regime, remains a fundamental challenge, especially beyond Davies generator-based approaches. Method: We introduce a novel quantum-to-classical reduction framework that maps the quantum Gibbs state preparation problem for CLHs to Gibbs sampling from a low-degree classical Hamiltonian, via a locality-preserving Hamiltonian embedding. Contribution/Results: This is the first efficient reduction establishing explicit correspondences between broad classes of CLHs—including defective toric codes—and tractable classical models. Leveraging this reduction, we construct a quantum circuit with time complexity O(n²) that prepares the Gibbs state in polynomial time even at low temperatures—surpassing temperature and model restrictions of prior methods. Our approach provides a crucial tool for thermal-state simulation and noise modeling of topological quantum memories.

4 citationsRead paper

Beyond Closure Models: Learning Chaotic-Systems via Physics-Informed Neural Operators

Aug 09, 2024arXiv.org

Long-term prediction of chaotic systems suffers from prohibitive computational cost and intrinsic approximation errors in closure models—arising from non-unique coarse-to-fine mappings. This work abandons the conventional coarse-grid-plus-closure paradigm and proposes an end-to-end physics-informed neural operator (PINO) framework that directly learns high-resolution spatiotemporal evolution maps. We establish, for the first time, a fundamental lower bound on the approximation error of closure models and develop a discretization-free, closure-free learning method with provable long-term statistical accuracy. Our approach integrates multi-scale collaborative training—coarse-grid pretraining followed by sparse full-resolution fine-tuning—and a PDE-residual-driven physics-constrained loss. Experiments demonstrate that, at ~10% relative error, our method achieves a 330× speedup over full-resolution simulations; compared to closure models trained on equivalent data, it reduces error by 5.4% and accelerates inference by 60×.

3 citationsRead paper
Recent publications

Latest Papers