Institution profile

Virginia Tech

Academic institutionnorthamerica · us
Official website
Research library1,104linked papers
Opportunities0open roles
Selected work

Representative Papers

A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge

Oct 18, 2023arXiv.org

Managing and retrieving high-dimensional vector data poses significant challenges, particularly as traditional databases fail to meet performance requirements and the need for tight integration with large language models (LLMs) intensifies. Method: This paper systematically surveys four major approximate nearest neighbor search (ANNS) paradigms—hashing, tree-based indexing, graph-based methods (e.g., HNSW), and quantization (PQ/SQ)—and integrates hybrid optimization strategies. Contribution/Results: It introduces, for the first time, a “Four-Dimensional Methodology” framework tailored for industrial deployment of vector databases, analyzing trade-offs among accuracy, latency, memory footprint, and scalability. The work constructs a structured knowledge graph covering 200+ ANNS algorithms and proposes a novel paradigm for deep synergy between vector databases and LLMs. Collectively, these contributions provide both theoretical foundations and practical guidelines for system selection, architectural design, and development of AI-native database systems.

62 citations3 influentialRead paper

Eye-tracked Virtual Reality: A Comprehensive Survey on Methods and Privacy Challenges

May 23, 2023arXiv.org

This paper addresses privacy leakage risks arising from the correlation between eye-tracking data and visual stimuli in VR environments. We systematically survey full-stack VR eye-tracking technologies—from pupil detection and gaze estimation to cognitive modeling—published between 2012 and 2022, alongside their associated privacy threats. First, we establish the first cross-disciplinary survey framework bridging VR eye-tracking and privacy protection, identifying three privacy-centric research directions. Second, we propose a novel co-design paradigm integrating eye movement authentication with data anonymization, synergizing computer vision, human-computer interaction modeling, differential privacy, adversarial generation, and biometric encryption. Third, we clarify the technological evolution trajectory and privacy threat landscape, and introduce quantifiable evaluation metrics and an implementable defense roadmap. Our work provides both theoretical foundations and practical guidelines for developing secure and trustworthy VR systems. (149 words)

21 citationsRead paper

Context Canvas: Enhancing Text-to-Image Diffusion Models with Knowledge Graph-Based RAG

Dec 12, 2024arXiv.org

Existing text-to-image (T2I) diffusion models suffer from limited training data coverage, hindering accurate generation of rare, complex, or culturally specific subjects. To address this, we propose a knowledge graph–driven retrieval-augmented generation (RAG) framework—the first to integrate graph-structured RAG into T2I modeling. Our approach dynamically retrieves fine-grained character attributes and relational context via a knowledge graph, employs graph neural networks for semantic alignment, and introduces a knowledge-guided self-correction mechanism to ensure visual consistency and semantic fidelity. Additionally, we incorporate ControlNet for precise spatial control and dynamic prompt engineering for adaptive textual conditioning. Extensive experiments on Flux, Stable Diffusion, and DALL-E demonstrate substantial improvements over baselines across multiple evaluation dimensions—particularly in cultural sensitivity, compositional accuracy, and fine-grained controllable editing.

3 citationsRead paper

A Sustainable AI Economy Needs Data Deals That Work for Generators

Jan 15, 2026

This study addresses the inequitable allocation of data value in the current machine learning value chain, where data generators receive inadequate compensation, thereby threatening the sustainability of the AI ecosystem. By analyzing 73 publicly documented data transactions, the work identifies three systemic structural flaws for the first time: lack of provenance traceability, asymmetric bargaining power, and static pricing mechanisms. To rectify these issues, the paper proposes the Equitable Data Value Exchange (EDVEX) framework, which integrates traceability, balanced bargaining capacity, and dynamic pricing to establish a minimal viable market institution. Empirical evidence reveals that existing transactions offer creators near-zero royalties and opaque terms, whereas EDVEX provides both a theoretical foundation and a practical pathway toward a sustainable, multi-stakeholder AI economy characterized by equitable value distribution.

1 citations1 influentialRead paper

Generalized matching decoders for 2D topological translationally-invariant codes

Mar 05, 2026

This work addresses the lack of efficient, high-performance decoders for two-dimensional translation-invariant topological quantum codes, such as bivariate bicycle codes. The authors propose a novel decoding framework based on coarse-grained mapping and graph matching, which maps the syndrome of a general translation-invariant code to an equivalent surface code excitation pattern. This approach extends graph-matching decoding—previously limited to specific models—to this broad class of topological codes for the first time. Theoretical analysis establishes that the decoder possesses provable error-correction capabilities and a non-zero code-capacity threshold. Numerical experiments demonstrate its ability to correct errors with weight up to a constant fraction of the code distance, achieving performance on bivariate bicycle codes comparable to belief propagation combined with ordered statistics decoding.

1 citationsRead paper
Recent publications

Latest Papers

The Future of Safety for SaMD

Sep 14, 2026

论文探讨了如何通过形式化验证方法提高软件驱动的人造器官的安全性，该方法能证明代码在所有允许执行情况下的正确性。

0 citationsRead paper