Institution profile

Rice University

Academic institutionnorthamerica · us
Official website
Research library594linked papers
Opportunities0open roles
Selected work

Representative Papers

Mixture of Experts Softens the Curse of Dimensionality in Operator Learning

Apr 13, 2024

To address the computational and memory bottlenecks imposed by the curse of dimensionality in high-dimensional operator learning, this paper proposes the Mixture-of-Experts Neural Operator (MoNO): a framework that decomposes a global nonlinear operator into multiple lightweight expert sub-operators, routed input-adaptively via a learnable decision-tree mechanism. Theoretically, we establish the first distributed universal approximation theorem, proving that MoNO uniformly approximates any Lipschitz-continuous nonlinear operator in Sobolev spaces; each expert’s depth, width, and rank scale as O(ε⁻¹), ensuring controllable memory footprint compatible with standard hardware. We further derive the first quantitative approximation rate for classical neural operators. Experiments and theory jointly demonstrate that MoNO achieves ε-accuracy with significantly reduced complexity, overcoming both expressive and deployability limitations inherent to monolithic neural operators.

20 citationsRead paper

Nonstationary Bandit Learning via Predictive Sampling

May 04, 2022International Conference on Artificial Intelligence and Statistics

This paper addresses the failure of Thompson sampling to maintain effective exploration in non-stationary multi-armed bandits due to its neglect of information timeliness. We propose Predictive Sampling, the first method to explicitly incorporate timeliness modeling into the Bayesian decision framework. It achieves adaptive exploration prioritization via dynamic prior updating and timeliness-weighted sampling. Theoretically, we derive the first Bayesian regret upper bound applicable to non-stationary environments and prove its boundedness. Computationally, we design a scalable approximate posterior inference mechanism. Experiments across diverse non-stationary settings—including abrupt and gradual distributional shifts—demonstrate that Predictive Sampling significantly outperforms classical Thompson sampling. The algorithm exhibits strong convergence properties, robustness to environmental dynamics, and practical scalability, making it suitable for real-world deployment.

19 citations3 influentialRead paper

Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions

Feb 28, 2024arXiv.org

Current large language models (LLMs) lack rigorous, clinically grounded evaluation of reasoning interpretability in complex medical decision-making. Method: We introduce JAMA Clinical Challenge and Medbullets—two high-difficulty, multiple-choice clinical benchmarks featuring authoritative, fine-grained expert explanations—the first such resources designed for real-world clinical scenarios. Evaluation employs zero-shot and few-shot prompting, automated explanation quality scoring, dual-blinded clinical expert assessment (Cohen’s κ = 0.82), and comparative analysis. Contribution/Results: Seven state-of-the-art LLMs exhibit substantially lower performance on these benchmarks than on conventional exam-style benchmarks. Their generated explanations frequently contain logical gaps and factual hallucinations, exposing critical deficiencies in clinical-grade causal reasoning and domain-specific knowledge integration—highlighting a fundamental gap between current LLM capabilities and safe, interpretable clinical deployment.

14 citations2 influentialRead paper

Local Level Dynamic Random Partition Models for Changepoint Detection

Jul 29, 2024

Addressing the challenges of modeling dynamic structures and detecting change points in multivariate time series (e.g., biomechanical and motion sensor data), this paper proposes a state-space-based stochastic partitioning model. Our method innovatively embeds a dynamic stochastic partitioning mechanism into the state equation, using Markovian latent variables to capture piecewise temporal dependencies. We design a non-marginalized false discovery rate (FDR) control strategy that explicitly accounts for statistical dependencies among change-point decisions, and support joint clustering of multi-view sequences. Integrating dynamic linear models, stochastic partition priors, and Gibbs sampling, the framework balances interpretability and computational efficiency. Evaluated on synthetic benchmarks and real human gesture phase data, our approach achieves significant improvements in change-point detection accuracy and robustness—reducing FDR by 20–35% over state-of-the-art methods—while demonstrating strong scalability.

3 citationsRead paper

Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration

Aug 14, 2025arXiv.org

Large language models (LLMs) struggle with semantic parsing in table understanding tasks due to structural complexity, while existing multi-agent SQL generation approaches suffer from schema misinterpretation, error propagation, and overreliance on execution feedback. To address these issues, we propose Chain-of-Query (CoQ), a novel multi-agent framework comprising three core components: (1) natural-language schema representation to mitigate structural noise; (2) clause-level progressive SQL generation that decouples logical units (e.g., SELECT, WHERE); and (3) a hybrid reasoning mechanism that explicitly separates symbolic execution from semantic inference, thereby reducing dependence on query execution outcomes. Extensive experiments across four state-of-the-art LLMs and five benchmark datasets demonstrate that CoQ significantly improves SQL correctness—reducing invalid SQL generation by up to 42.6%—and achieves superior robustness and generalization in table-aware semantic parsing.

2 citationsRead paper
Recent publications

Latest Papers