Institution profile

Chongqing University

Academic institutionasia · cn
Official website
Research library438linked papers
Opportunities0open roles
Selected work

Representative Papers

Open Data in the Digital Economy: An Evolutionary Game Theory Perspective

Jun 01, 2024IEEE Transactions on Computational Social Systems

Existing research on open data–driven sustainable development overlooks the critical role of data intermediaries—particularly regulatory entities—in governing data ecosystems. Method: This study constructs a tripartite evolutionary game model integrating data providers, users, and regulators—the first systematic incorporation of regulators into open data literature—to characterize multi-stakeholder co-evolutionary dynamics. It employs replicator dynamics analysis, numerical simulation, and sensitivity testing to examine nonlinear interactions among regulatory incentives, user costs, and data value. Contribution/Results: The analysis identifies multiple evolutionarily stable strategies (ESS) and quantifies threshold effects: regulatory reward-penalty intensity and users’ data mining capability exhibit nonlinear, bifurcation-like impacts on cooperation rates. Findings provide empirically grounded theoretical foundations for designing incentive-compatible platform mechanisms and evidence-based data governance policies to advance sustainable development through open data.

13 citationsRead paper

Landmark Guided 4D Facial Expression Generation

Nov 28, 2023SIGGRAPH ASIA Posters

Existing methods for 4D facial expression generation exhibit limited robustness in cross-identity generalization. To address this issue, this work proposes LM-4DGAN, a novel framework that, for the first time, leverages neutral-face landmarks as a guiding signal for expression synthesis. The model integrates an identity discriminator and a landmark autoencoder to enhance identity invariance, while incorporating a cross-attention mechanism within the displacement decoder to enable personalized adaptation to specific identities. Built upon a Wasserstein GAN (WGAN) architecture, LM-4DGAN significantly improves both the robustness and expressiveness of cross-identity facial animation, outperforming current approaches that rely on label-based or speech-driven conditioning.

4 citationsRead paper

UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs

Apr 22, 2025The Web Conference

Real-world web pages exhibit complex, verbose HTML/CSS structures, hindering multimodal large language models (MLLMs) from effectively modeling long-range UI topological relationships. To address this, we propose UICopilot: an end-to-end, hierarchical frontend code generation framework. Its core contributions are: (1) a hierarchical generation paradigm that decouples output into three sequential stages—layout, component instantiation, and styling; (2) a structure-aware, multi-granularity prompting mechanism that explicitly encodes UI hierarchy and spatial relations; and (3) an MLLM architecture integrating a vision encoder with hierarchical instruction fine-tuning. Evaluated on WebCode2M—a large-scale real-world webpage dataset—UICopilot achieves a 32% improvement over baselines (e.g., GPT-4V) in automated metrics and is preferred by 87% of human evaluators. These results demonstrate substantial advances in both practical usability and structural fidelity for multimodal UI code generation.

2 citationsRead paper

PAMAS: Self-Adaptive Multi-Agent System with Perspective Aggregation for Misinformation Detection

Feb 03, 2026

This work addresses the challenges posed by the high diversity and context dependence of misinformation on social media, which often overwhelms conventional multi-agent systems and obscures subtle deceptive cues. To overcome these limitations, the authors propose an adaptive multi-agent framework featuring a tripartite role structure—auditor, coordinator, and decision-maker—augmented with a perspective-aware hierarchical aggregation mechanism and an adaptive topology optimization strategy. This design effectively amplifies anomalous signals while integrating heterogeneous viewpoints. Leveraging large language model–driven collaborative reasoning, dynamic routing, and an evolving memory mechanism, the approach significantly outperforms state-of-the-art methods across multiple benchmark datasets, achieving superior detection accuracy and reasoning efficiency. The proposed solution offers a scalable and robust paradigm for misinformation detection in complex social media environments.

1 citationsRead paper

CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

Feb 02, 2026

This work addresses the computational burden imposed by long text sequences in large language models for code understanding. It presents the first systematic exploration of rendering source code as images and feeding them into multimodal large language models, leveraging the compressibility of visual representations to substantially reduce context length and computational cost while preserving essential semantic information. By incorporating visual cues such as syntax highlighting, the approach achieves up to an 8× token compression ratio on code completion tasks and even outperforms the original text-based input at a 4× compression rate. Furthermore, it demonstrates robust or slightly superior performance on code clone detection, validating the efficacy and potential of image-based modalities for efficient code understanding.

1 citationsRead paper
Recent publications

Latest Papers