Jingyu Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jingyu Xiao has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Yong Jiang
Tsinghua University
8 shared publications - Qing Li
Pengcheng Laboratory, Shenzhen, China
7 shared publications - Dan Zhao
Pengcheng Laboratory, Shenzhen, China
6 shared publications - Michael R. Lyu
The Chinese University of Hong Kong
4 shared publications - Qingsong Zou
Tsinghua University
4 shared publications - Yintong Huo
Singapore Management University, Singapore
4 shared publications
Latest Publications
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 3445-3449
UIBenchKit: A Unified Toolkit for Design-to-Code Model Evaluation
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 3445-3449
Open AccessUIBenchKit: A Unified Toolkit for Design-to-Code Model Evaluation
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 726-738
From Runnable Code to Shippable Applications: Test-Driven Development for Full-Stack Web Application Generation
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 726-738
Open AccessFrom Runnable Code to Shippable Applications: Test-Driven Development for Full-Stack Web Application Generation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 5638-5649
Component-based Reusable UI Code Generation for Complex Websites via Semantic Segmentation and Fine-grained Feedback
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 5638-5649
Open AccessComponent-based Reusable UI Code Generation for Complex Websites via Semantic Segmentation and Fine-grained Feedback
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 2396-2418
EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation
Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in UI2Code tasks (i.e., generating code from UI mockups), significantly enhancing website development efficiency. However, UI2Code tasks incur substantially higher computational overhead compared to traditional code generation tasks. This overhead is primarily driven by the large number of input image tokens required to represent complex visual designs and the extensive volume of output code tokens needed to describe complete webpage structures. In this paper, we conduct a comprehensive preliminary study on popular MLLMs for UI2Code tasks, identifying significant redundancies in both image and code tokens. We observe that these redundancies not only exacerbate computational complexity but also hinder the model’s ability to focus on key UI elements, leading to excessively lengthy and often invalid HTML files. To address these challenges, we propose EfficientUICoder, a bidirectional compression framework designed for efficient UI code generation. First, we introduce an Element and Layout-aware Token Compression method, which preserves essential UI element and layout information by detecting element regions and constructing a UI element tree for efficient representation. Second, we design a Region-aware Token Refinement strategy that refines selected tokens by leveraging attention scores to evaluate semantic importance, discarding low-attention tokens from selected regions while integrating high-attention tokens from unselected regions. Third, we develop an Adaptive Duplicate Token Suppression mechanism, which dynamically modulates token probabilities during decoding by tracking HTML/CSS code structure frequencies and applying exponential penalty strategies to minimize repetitive generation. Extensive experiments demonstrate that EfficientUICoder achieves a 55%-60% compression ratio without compromising the quality of the generated webpages, effectively reducing output code redundancy. In terms of efficiency, EfficientUICoder achieves superior improvements, reducing computational cost by up to 44.9%, generated tokens by up to 41.4%, prefill time by up to 46.6%, and inference time by up to 48.8% on 34B-level MLLMs. Code is available at https://github.com/WebPAI/EfficientUICoder.
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 2396-2418
Open AccessEfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation
Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in UI2Code tasks (i.e., generating code from UI mockups), significantly enhancing website development efficiency. However, UI2Code tasks incur substantially higher computational overhead compared to traditional code generation tasks. This overhead is primarily driven by the large number of input image tokens required to represent complex visual designs and the extensive volume of output code tokens needed to describe complete webpage structures. In this paper, we conduct a comprehensive preliminary study on popular MLLMs for UI2Code tasks, identifying significant redundancies in both image and code tokens. We observe that these redundancies not only exacerbate computational complexity but also hinder the model’s ability to focus on key UI elements, leading to excessively lengthy and often invalid HTML files. To address these challenges, we propose EfficientUICoder, a bidirectional compression framework designed for efficient UI code generation. First, we introduce an Element and Layout-aware Token Compression method, which preserves essential UI element and layout information by detecting element regions and constructing a UI element tree for efficient representation. Second, we design a Region-aware Token Refinement strategy that refines selected tokens by leveraging attention scores to evaluate semantic importance, discarding low-attention tokens from selected regions while integrating high-attention tokens from unselected regions. Third, we develop an Adaptive Duplicate Token Suppression mechanism, which dynamically modulates token probabilities during decoding by tracking HTML/CSS code structure frequencies and applying exponential penalty strategies to minimize repetitive generation. Extensive experiments demonstrate that EfficientUICoder achieves a 55%-60% compression ratio without compromising the quality of the generated webpages, effectively reducing output code redundancy. In terms of efficiency, EfficientUICoder achieves superior improvements, reducing computational cost by up to 44.9%, generated tokens by up to 41.4%, prefill time by up to 46.6%, and inference time by up to 48.8% on 34B-level MLLMs. Code is available at https://github.com/WebPAI/EfficientUICoder.
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2182-2190
Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2182-2190
Open AccessBenchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1751-1762
SmartGen: Synthesizing Context-Aware User Behavior Data for Adaptive Smart Home Intelligence
As smart homes become increasingly prevalent, intelligent models are widely used for tasks such as anomaly detection and behavior prediction. These models are typically trained on static datasets, making them brittle to behavioral drift caused by seasonal changes, lifestyle shifts, or evolving routines. However, collecting new behavior data for retraining is often impractical due to its slow pace, high cost, and privacy concerns. In this paper, we propose SmartGen, an LLM-based framework that synthesizes context-aware user behavior data to support continual adaptation of downstream smart home models. SmartGen consists of four key components. First, we design a Time and Semantic-aware Split module to divide long behavior sequences into manageable, semantically coherent subsequences under dual time-span constraints. Second, we propose Semantic-aware Sequence Compression to reduce input length while preserving representative semantics by clustering behavior mapping in latent space. Third, we introduce Graph-guided Sequence Synthesis, which constructs a behavior relationship graph and encodes frequent transitions into prompts, guiding the LLM to generate data aligned with contextual changes while retaining core behavior patterns. Finally, we design a Two-stage Outlier Filter to identify and remove implausible or semantically inconsistent outputs, aiming to improve the factual coherence and behavioral validity of the generated sequences. Experiments on three real-world datasets demonstrate that SmartGen significantly enhances model performance on anomaly detection and behavior prediction tasks under behavioral drift, with anomaly detection improving by 85.43% and behavior prediction by 70.51% on average. The code is available at https://github.com/xzyvoid/SmartGen.
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1751-1762
Open AccessSmartGen: Synthesizing Context-Aware User Behavior Data for Adaptive Smart Home Intelligence
As smart homes become increasingly prevalent, intelligent models are widely used for tasks such as anomaly detection and behavior prediction. These models are typically trained on static datasets, making them brittle to behavioral drift caused by seasonal changes, lifestyle shifts, or evolving routines. However, collecting new behavior data for retraining is often impractical due to its slow pace, high cost, and privacy concerns. In this paper, we propose SmartGen, an LLM-based framework that synthesizes context-aware user behavior data to support continual adaptation of downstream smart home models. SmartGen consists of four key components. First, we design a Time and Semantic-aware Split module to divide long behavior sequences into manageable, semantically coherent subsequences under dual time-span constraints. Second, we propose Semantic-aware Sequence Compression to reduce input length while preserving representative semantics by clustering behavior mapping in latent space. Third, we introduce Graph-guided Sequence Synthesis, which constructs a behavior relationship graph and encodes frequent transitions into prompts, guiding the LLM to generate data aligned with contextual changes while retaining core behavior patterns. Finally, we design a Two-stage Outlier Filter to identify and remove implausible or semantically inconsistent outputs, aiming to improve the factual coherence and behavioral validity of the generated sequences. Experiments on three real-world datasets demonstrate that SmartGen significantly enhances model performance on anomaly detection and behavior prediction tasks under behavioral drift, with anomaly detection improving by 85.43% and behavior prediction by 70.51% on average. The code is available at https://github.com/xzyvoid/SmartGen.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5029-5038
Aligning and Balancing ID and Multimodal Representations for Recommendation
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5029-5038
Open AccessAligning and Balancing ID and Multimodal Representations for Recommendation
- 6 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Magazine
- Vol. 8 (6) , 17-23
Synthetic User Behavior Sequence Generation With Large Language Models for Smart Homes
In recent years, as smart home systems have become more widespread, security concerns within these environments have become a growing threat. Currently, most smart home security solutions, such as anomaly detection and behavior prediction models, are trained using fixed datasets that are precollected. However, the process of dataset collection is time-consuming and lacks the flexibility needed to adapt to the constantly evolving smart home environment. Additionally, the collection of personal data raises significant privacy concerns for users. Lately, large language models (LLMs) have emerged as a powerful tool for a wide range of tasks across diverse application domains, thanks to their strong capabilities in natural language processing, reasoning, and problem-solving. In this paper, we propose an LLM-based synthetic dataset generation IoTGen framework to enhance the generalization of downstream smart home intelligent models. By generating new synthetic datasets that reflect changes in the environment, smart home intelligent models can be retrained to overcome the limitations of fixed and outdated data, allowing them to better align with the dynamic nature of real-world home environments. Specifically, we first propose a Structure Pattern Perception Compression (SPPC) method tailored for IoT behavior data, which preserves the most informative content in the data while significantly reducing token consumption. Then, we propose a systematic approach to create prompts and implement data generation to automatically generate IoT synthetic data with normative and reasonable properties, assisting task models in adaptive training to improve generalization and real-world performance.
- 6 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Magazine
- Vol. 8 (6) , 17-23
Synthetic User Behavior Sequence Generation With Large Language Models for Smart Homes
In recent years, as smart home systems have become more widespread, security concerns within these environments have become a growing threat. Currently, most smart home security solutions, such as anomaly detection and behavior prediction models, are trained using fixed datasets that are precollected. However, the process of dataset collection is time-consuming and lacks the flexibility needed to adapt to the constantly evolving smart home environment. Additionally, the collection of personal data raises significant privacy concerns for users. Lately, large language models (LLMs) have emerged as a powerful tool for a wide range of tasks across diverse application domains, thanks to their strong capabilities in natural language processing, reasoning, and problem-solving. In this paper, we propose an LLM-based synthetic dataset generation IoTGen framework to enhance the generalization of downstream smart home intelligent models. By generating new synthetic datasets that reflect changes in the environment, smart home intelligent models can be retrained to overcome the limitations of fixed and outdated data, allowing them to better align with the dynamic nature of real-world home environments. Specifically, we first propose a Structure Pattern Perception Compression (SPPC) method tailored for IoT behavior data, which preserves the most informative content in the data while significantly reducing token consumption. Then, we propose a systematic approach to create prompts and implement data generation to automatically generate IoT synthetic data with normative and reasonable properties, assisting task models in adaptive training to improve generalization and real-world performance.
- 5 October 2024
- Published by Elsevier in Computer Networks
- Vol. 255
Themis: A passive-active hybrid framework with in-network intelligence for lightweight failure localization
- 5 October 2024
- Published by Elsevier in Computer Networks
- Vol. 255
Themis: A passive-active hybrid framework with in-network intelligence for lightweight failure localization
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 3551-3562
Make Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes via Loss-guided Mask
Smart homes, powered by the Internet of Things, offer great convenience but also pose security concerns due to abnormal behaviors, such as improper operations of users and potential attacks from malicious attackers. Several behavior modeling methods have been proposed to identify abnormal behaviors and mitigate potential risks. However, their performance often falls short because they do not effectively learn less frequent behaviors, consider temporal context, or account for the impact of noise in human behaviors. In this paper, we propose SmartGuard, an autoencoder-based unsupervised user behavior anomaly detection framework. First, we design a Loss-guided Dynamic Mask Strategy (LDMS) to encourage the model to learn less frequent behaviors, which are often overlooked during learning. Second, we propose a Three-level Time-aware Position Embedding (TTPE) to incorporate temporal information into positional embedding to detect temporal context anomaly. Third, we propose a Noise-aware Weighted Reconstruction Loss (NWRL) that assigns different weights for routine behaviors and noise behaviors to mitigate the interference of noise behaviors during inference. Comprehensive experiments demonstrate that SmartGuard consistently outperforms state-of-the-art baselines and also offers highly interpretable results.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 3551-3562
Open AccessMake Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes via Loss-guided Mask
Smart homes, powered by the Internet of Things, offer great convenience but also pose security concerns due to abnormal behaviors, such as improper operations of users and potential attacks from malicious attackers. Several behavior modeling methods have been proposed to identify abnormal behaviors and mitigate potential risks. However, their performance often falls short because they do not effectively learn less frequent behaviors, consider temporal context, or account for the impact of noise in human behaviors. In this paper, we propose SmartGuard, an autoencoder-based unsupervised user behavior anomaly detection framework. First, we design a Loss-guided Dynamic Mask Strategy (LDMS) to encourage the model to learn less frequent behaviors, which are often overlooked during learning. Second, we propose a Three-level Time-aware Position Embedding (TTPE) to incorporate temporal information into positional embedding to detect temporal context anomaly. Third, we propose a Noise-aware Weighted Reconstruction Loss (NWRL) that assigns different weights for routine behaviors and noise behaviors to mitigate the interference of noise behaviors during inference. Comprehensive experiments demonstrate that SmartGuard consistently outperforms state-of-the-art baselines and also offers highly interpretable results.