arXiv subjects

Haojie Wu

Publications and source records attributed to Haojie Wu.

4 recordsLinked to original sources

arXiv2026

Caption Injection for Optimization in Generative Search Engine

Generative Search Engine (GSE) leverages the Retrieval-Augmented Generation (RAG) technique and the Large Language Model (LLM) to integrate multi-source information and provide users with accurate and comprehensive responses. Unlike traditional search engines that present results in ranked lists, GSE shifts users' attention from sequential browsing to content-driven subjective perception, not only driving a paradigm shift in information retrieval but also highlighting the importance of enhancing the subjective visibility of content in generative search. In this context, Generative Search Engine Optimization (G-SEO) methods have emerged as a new research focus. With the rapid advancement of Multimodal Retrieval-Augmented Generation (MRAG) techniques, GSE can now efficiently integrate text, images, audio, and video, producing richer responses that better satisfy complex information needs. Existing G-SEO methods, however, remain limited to text-based optimization and fail to fully exploit multimodal data. To address this gap, we propose Caption Injection, the first multimodal G-SEO approach, which extracts captions from images and injects them into textual content, integrating visual semantics to enhance the subjective visibility in generative search. We systematically evaluate Caption Injection on MRAMG, a benchmark for MRAG, under both unimodal and multimodal settings. Experimental results show that Caption Injection significantly outperforms text-only G-SEO baselines under the G-EVAL metric, effectively improving the subjective visibility of content perceived by users, and demonstrating the practical benefits of multimodal information in G-SEO. The source code for this work is openly available at https://github.com/GrayChan04/Caption-Injection.

cs.IR↗

arXiv2026

Role-Augmented Intent-Driven Generative Search Engine Optimization

Generative Search Engines (GSEs), powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), are reshaping information retrieval. While commercial systems (e.g., BingChat, Perplexity.ai) demonstrate impressive semantic synthesis capabilities, their black-box nature fundamentally undermines established Search Engine Optimization (SEO) practices. Content creators face a critical challenge: their optimization strategies, effective in traditional search engines, are misaligned with generative retrieval contexts, resulting in diminished visibility. To bridge this gap, we propose a Role-Augmented Intent-Driven Generative Search Engine Optimization (G-SEO) method, providing a structured optimization pathway tailored for GSE scenarios. Our method models search intent through reflective refinement across diverse informational roles, enabling targeted content enhancement. To better evaluate the method under realistic settings, we address the benchmarking limitations of prior work by: (1) extending the GEO dataset with diversified query variations reflecting real-world search scenarios and (2) introducing G-Eval 2.0, a 6-level LLM-augmented evaluation rubric for fine-grained human-aligned assessment. Experimental results demonstrate that search intent serves as an effective signal for guiding content optimization, yielding significant improvements over single-aspect baseline approaches in both subjective impressions and objective content visibility within GSE responses.

cs.IR↗

arXiv2023

Many-body non-Hermitian skin effect under dynamic gauge coupling

We study an atom-cavity hybrid system where fermionic atoms in a one-dimensional lattice are subject to a cavity-induced dynamic gauge potential. The gauge coupling leads to highly-degenerate steady states in which the fermions accumulate to one edge of the lattice under an open boundary condition. Such a phenomenon originates from the many-body Liouvillian superoperator of the system, which, being intrinsically non-Hermitian, is unstable against boundary perturbations and manifests the non-Hermitian skin effect. Contrary to the single-body case, the steady state of a multi-atom system is approached much slower under the open boundary condition, as the long-time damping of the cavity mode exhibits distinct rates at different times. This stage-wise slowdown is attributed to the competition between light-assisted hopping and the dynamic gauge coupling, which significantly reduces the steady-state degeneracy under the open boundary condition, as distinct hosts of quasi-steady states dominate the dynamics at different time scales.

cond-mat.quant-gas↗

arXiv2023

Deepfake in the Metaverse: An Outlook Survey

We envision deepfake technologies, which synthesize realistic fake images and videos, will play an important role in the future metaverse. While enhancing users' immersion and experience with synthesized virtual characters and scenes, deepfake can cause serious consequences if used for fraud, impersonation, and dissemination of fake information. In this paper, we introduce the principles, applications, and risks of deepfake technology, and propose some countermeasures to help users and developers in the metaverse deal with the challenges brought by deepfake technologies. Further, we provide an outlook on the future development of deepfake in the metaverse.

cs.HC↗