Institution profile

Harvard University

Academic institutionnorthamerica · us
Official website
Research library2,139linked papers
Opportunities0open roles
Selected work

Representative Papers

AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection

Oct 29, 2023International Conference on Learning Representations

Zero-shot anomaly detection (ZSAD) aims to identify anomalies across domains without access to target-domain training samples; however, its generalizability is severely hindered by substantial discrepancies in foreground objects, anomaly appearances, and background distributions. To address this, we propose a CLIP-based universal ZSAD framework. Our method introduces the first object-agnostic text prompt learning mechanism, decoupling foreground semantics from normal/abnormal discrimination modeling. We further design learnable, domain-agnostic “normal” and “abnormal” text prompts and leverage vision-language feature alignment to enable zero-shot anomaly scoring and pixel-level localization. Critically, our approach requires no target-domain annotations or fine-tuning. Extensive experiments across 17 industrial defect and medical imaging datasets demonstrate significant improvements over existing ZSAD methods, achieving both strong cross-domain generalization and high localization accuracy.

114 citations20 influentialRead paper

Experimental Design under Network Interference

Mar 18, 2020

This paper addresses two-stage experimental design under network spillover effects, aiming to obtain unbiased estimates of the average direct effect, spillover effect, and their interaction. To mitigate identification bias arising from spillovers between adjacent nodes and unobserved local confounding, we propose a novel two-wave hierarchical optimization framework: the first stage uses a small-scale pilot to estimate the network variance structure; the second stage adaptively optimizes unit selection and treatment assignment based on this estimate. Theoretically, we rigorously characterize the no-unmeasured-confounding condition, establish an asymptotic scaling relationship between pilot and main experiment sizes, and derive consistency, asymptotic normality, and a minimax regret bound for the proposed estimators. Integrating causal inference, network analysis, and asymptotic statistics, our method substantially reduces finite-sample estimation variance—outperforming state-of-the-art alternatives in both simulations and real-world networks—thereby empirically validating its theoretical guarantees.

37 citations1 influentialRead paper

Application-Driven Innovation in Machine Learning

Mar 26, 2024International Conference on Machine Learning

Application-driven machine learning (ML) research has been systematically undervalued in academia, leading to a growing disconnect between algorithmic innovation and real-world needs; this marginalization is reinforced by structural biases in peer review, faculty hiring, and pedagogy. Method: This paper introduces, for the first time, a formally defined “application-driven ML research paradigm,” elucidating its complementary relationship with the dominant methodology-driven paradigm. Drawing on interdisciplinary frameworks from education theory, research governance, and ML practice—and substantiated by empirical case studies and institutional critique—it diagnoses three systemic barriers hindering such research. Contribution/Results: The core contribution is a set of actionable, process-level interventions to reform academic evaluation systems, grounded in both theoretical analysis and pragmatic implementation pathways. These proposals have already catalyzed curricular reforms in AI education and adjustments to national funding review criteria across multiple universities, fostering cross-domain collaboration and methodological feedback loops between application domains and core ML research.

22 citations2 influentialRead paper

Linear space streaming lower bounds for approximating CSPs

Jun 24, 2021Electron. Colloquium Comput. Complex.

This work investigates the approximability threshold of constraint satisfaction problems (CSPs) in the streaming model. For $n$-variable CSPs over domain ${0,dots,q-1}$ with $O(n)$ constraints, we prove that any algorithm achieving approximation ratio strictly better than the trivial $1/q$ requires $Omega(n)$ space—establishing the first linear-space lower bound for approximation ratios below $1/2$. Methodologically, we extend the Kapralov–Krachun linear lower-bound technique to general CSPs (surpassing prior $Omega(sqrt{n})$ bounds) via modular-$q$ linear equation encoding, communication complexity analysis, and pseudorandom hard-instance reduction. This yields optimal $q^{-(k-1)}$ inapproximability for Max $k$-LIN mod $q$ with $k>2$, $q>2$. Our results uniformly characterize the streaming hardness of broad CSP subclasses: all nontrivial approximation requires essentially linear space, significantly advancing the theoretical understanding of streaming algorithm limitations.

15 citationsRead paper

Licensing Open Government Data

May 08, 2017

This study addresses the dual challenges confronting Open Government Data (OGD) licensing: ambiguous legal status and inadequate cross-jurisdictional adaptability, revealing its fundamentally policy-driven nature—distinct from commercial licensing or public sharing paradigms. Through the first comparative analysis of OGD license terms across 32 countries, coupled with policy document interpretation and intellectual property law theoretical modeling, we identify critical jurisdictional divergences, including database rights regimes and waivability of moral rights. We innovatively propose a “Policy–Jurisdiction” two-dimensional adaptation framework and derive licensing design principles that jointly ensure legal validity, cross-jurisdictional consistency, and reusability efficacy. The findings elevate OGD licenses from technical appendices to core instruments of information policy, substantially enhancing legal certainty and economic conversion rates of government data assets.

7 citations1 influentialRead paper
Recent publications

Latest Papers