Yixin Li

Prof. Dr. Yixin Li

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 December 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JLJun Liang
Jun Liang
YLYixin Li
Yixin Li
ZXZhileng Xiong
Zhileng Xiong
QHQing Huang
Qing Huang
We propose a human-in-the-loop AI-generated content (AIGC) system to advance lacquerware design innovation by merging artisan knowledge with controllable diffusion models. Traditional lacquerware design faces challenges in balancing heritage preservation and creative exploration, where artisans often struggle with limited inspiration sources and time-consuming manual processes. The proposed system tackles these problems by employing a closed-loop workflow that integrates AI-driven creation and human adjustment, which fosters iterative cooperation between artisans and the AI engine. The system architecture consists of a front-end interface, an AI engine operating on the back end, and a carefully assembled database of historical and modern lacquerware designs, which undergo preprocessing steps such as normalization, background removal, and detailed annotation to document stylistic and compositional features. Essentially, a diffusion model refined through LoRA adaptation for specialized domain control produces high-quality lacquerware designs without compromising their aesthetic coherence. Furthermore, the system integrates multi-modal control mechanisms, which comprise text-to-image prompts for stylistic direction and image-to-image operations with ControlNet to achieve structural accuracy, thereby granting artisans the capability to submit sketches or reference compositions that the AI subsequently augments with elaborate details. The interactive user interface includes an inspiration gallery, a canvas with dynamic properties, and adjustable parameter controls, granting artisans the ability to efficiently investigate a wide range of design alternatives. Our key achievements consist of an innovative implementation of controllable diffusion models in cultural heritage design, a lacquerware dataset with detailed annotations, and a fine-tuning method empirically proven to elevate generation quality. Experiments show the system’s capacity to generate culturally consistent designs while markedly decreasing the time required for artisans to conceptualize their work. This work holds importance due to its capacity to connect traditional craftsmanship with contemporary AI technologies, thereby promoting innovation while preserving the genuine qualities of lacquerware art. The system broadens availability of sophisticated design tools, thereby hastening creative processes and creating fresh opportunities for cross-disciplinary studies in AI-driven cultural heritage conservation.

17 July 2026 in Frontiers in Psychology
Verified
Journal Article
Open access
PDF file
JLJun Liang
Jun Liang
YLYixin Li
Yixin Li
ZXZhileng Xiong
Zhileng Xiong
Generative AI (AIGC) is fundamentally reshaping the landscape of digital content, yet its specific predictive relationship with the cultural identity of “digital natives” (Generation Z) remains underexplored compared to traditional User-Generated Content (UGC). While AIGC offers efficiency and aesthetic novelty, it lacks the inherent “human touch” of UGC. This study investigates this divergence by analyzing 11,628 comments from the Douyin platform. We employed a mixed-method approach combining semantic network analysis and structural equation modeling (SEM) to compare user responses across emotional, technological, and social dimensions. Our findings reveal a distinct “two-path” mechanism: while UGC fosters identity through a “Warm Path” of emotional resonance, AIGC is structurally associated with a significantly more robust identity profile via a “Cool Path” predicted by technical curiosity and exclusive topic circling. Crucially, we identify an “Authenticity Paradox”: the lack of traditional human touch in AIGC does not alienate Generation Z; rather, the resulting “mindful friction”—quantified by a significant negative path effect between sentiment and identity ( β = − 0.370 ) —functions as a subcultural filter.

19 September 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
TYTingting Yu
Tingting Yu
YLYixin Li
Yixin Li
The preservation of Intangible Cultural Heritage (ICH) often struggles with static archival methods and a growing disconnect from contemporary design practices. While generative artificial intelligence offers a rapid mechanism to translate traditional aesthetics into modern forms, off-the-shelf models frequently suffer from cultural bias and overrepresent Western-centric data, leading to inauthentic outputs. This study introduces a pedagogical framework combining Generative AI with Value-Sensitive Design (VSD) to address these challenges in higher education. Focusing on two regional heritages—Xiang Embroidery and Changsha Kiln ceramics—we conducted a 12-week quasi-experimental study with 118 design students. The experimental group utilized a custom AI pipeline employing multimodal LLM tagging, Low-Rank Adaptation (LoRA) fine-tuning, and ControlNet spatial constraints to ensure algorithmic outputs remained culturally accurate. Quantitative results revealed that students using the VSD-guided AI demonstrated statistically significant improvements in aesthetic appreciation, design implementation, and cultural identity compared to the control group using traditional methods. Qualitative feedback indicated that the AI pipeline effectively lowered technical drafting barriers, shifting students’ cognitive focus toward cultural curation and critical aesthetic judgment. The findings suggest that ethically constrained generative models effectively support heritage-oriented design learning in regional universities. Rather than attempting to “revitalize” the heritage itself, this structured approach provides students with a culturally grounded framework. It allows them to safely engage with traditional aesthetics and translate these elements into contemporary formats without risking cultural dilution.