Publications

Publications

Recent selected publications (2024–2026). The complete list, including earlier work, is on the faculty page.

Full publication list (faculty page)

2026
  • Instance-Adaptive Graph-Guided Registration via Dynamic Anatomical Reasoning. Y. Dai, Z. Huang, X. Wang, W. Huang. MICCAI 2026.
  • DRIP: Defending Prompt Injection via Token-wise Representation Editing and Residual Fusion. R. Liu, Y. Kin, Z. Huang, J. Dong. ACM CCS 2026.
  • Addressing Graph Heterogeneity and Heterophily from a Spectral Perspective. K. Lu, Y. Yu, R. Guo, N. Cheng, Z. Huang, Y. Ma, M. Liang, Y. Wang, X. Qin, Y. Ren, T.-S. Chua. Neurocomputing, vol. 683, 2026 (Elsevier).
  • Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach. Y. Liao, Y. Cao, Y. Zhang, W. He, Y. Xiao, X. Du, Z. Huang, J. S. Dong. CVPR 2026.
  • L-Tree: Single-View 3D Tree Reconstruction from Structure Masks via Hierarchical L-System Inference. Z. Lin, Y. Ang, Z. Xu, C. T. Thomas Ho, Z. Huang. CVPRW GenRecon3D 2026.
  • HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities. X. Ren, P. Jiang, K. Li, Z. Huang, X. Du, J. Jiang, Z. Xing, J. Sun, Y. Terry Zhuo. ICLR 2026.
  • TrainRef: Curating Data with Label Distribution and Minimal Reference for Accurate Prediction and Reliable Confidence. M. Ma, R. Liu, Y. Lin, Z. Huang, J. S. Dong. ICLR 2026.
  • CTBench: Cryptocurrency Time Series Generation Benchmark. Y. Ang, Q. Wang, Q. Huang, Y. Bao, X. Xi, A. K. H. Tung, J. Chen, Z. Huang. ICLR 2026.
  • Directional Time Series Editing via Retrieval-Guided Jacobian-Vector Inference. Y. Bao, Y. Ang, Q. Huang, A. K. H. Tung, Z. Huang. KDD 2026 (Research Track).
  • RFOD: Random Forest-based Outlier Detection for Mixed-Type Tabular Data. Y. Ang, P. Yao, Y. Bao, Y. Feng, Q. Huang, A. K. H. Tung, Z. Huang. ICDE 2026.
  • NB2P: Generating Data Science Pipelines from Computational Notebooks. H. Gao, Q. T. Ta, T. T. A. Dinh, N. M. Ho, Z. Huang, B. C. Ooi. ICSE 2026.
  • EditFlow: Benchmarking and Optimizing Code Edit Recommendation Systems via Reconstruction of Developer Flows. C. Y. Liu, Y. Lin, J. Chang, J. Liu, B. Qi, B. Jiang, Z. Huang, J. S. Dong. OOPSLA 2026.
  • Tele-Omni: A Unified Multimodal Framework for Video Generation and Editing. J. Liu, T. Li, X. Cao, et al., Z. Huang, et al., X. Li. Technical report, arXiv:2602.09609.
2025
  • 3D-OTT: Texture Transfer for 3D Objects from a Single Reference Image. X. Cao, B. Lin, B. Wang, Z. Huang, R. T. Tan. NeurIPS 2025.
  • CMS-VAE: A Strategy-aware Variational Autoencoder for High-Fidelity Crypto Market Simulation. Y. Ang, Y. Bao, Q. Huang, Q. Wang, X. Xi, S. Lu, A. K. H. Tung, Z. Huang. ACM ICAIF 2025.
  • Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction. C. Y. Liu, Y. Lin, Y. Huang, J. Chang, B. Qi, B. Jiang, Z. Huang, J. S. Dong. ASE 2025.
  • CoEdPilot: Interactively Recommending Project-Wise Code Edits. Y. H. Huang, C. Y. Liu, Y. Lin, Y. F. Cai, B. Jiang, P. Yang, Z. Huang, J. S. Dong. Journal of Computer Science and Technology, 2025.
  • SSNeRF: Sparse-View Semi-supervised Neural Radiance Fields with Augmentation. X. Cao, B. Lin, B. Wang, Z. Huang, R. T. Tan. BMVC 2025.
  • ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use. K. Li, Z. Meng, H. Lin, Z. Luo, Y. Tian, J. Ma, Z. Huang, T.-S. Chua. ACM MM 2025 (Oral).
  • DeepMolTex: Deep Alignment of Molecular Graphs with Large Language Models via Mixture of Modality Experts. M. Yan, Y. Yu, R. Zhang, Z. Liu, R. Zhang, Y. Ren, K. Lu, Z. Huang, F. Luo, Z. Cai. ACM MM 2025.
  • AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Meme Harmfulness. Z. Chen, H. Lin, K. Li, Z. Luo, Z. Ye, G. Chen, Z. Huang, J. Ma. ACL 2025 (Main).
  • Bridging 3D Editing and Geometry-Consistent Paired Dataset Creation for 2D Nighttime-to-Daytime Translation. X. Cao, Y. Zhao, R. T. Tan, Z. Huang. CVPR 2025 Workshop SyntaGen.
  • A Trained Physics-Informed Neural Networks (PINNs) Method for the Phase-Field Model in the Allen–Cahn Framework. L. Song, X. Chen, Z. Huang, B. Du. AI4X 2025 (Oral).
  • Machine Learning-based Optimization for Molten Pool Dynamics in Laser Manufacturing. L. Song, Z. Huang, X. Chen. ICLR 2025 Workshop XAI4Science.
  • MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems. K. Li, Y. Tian, Q. Hu, Z. Luo, Z. Huang, J. Ma. EMNLP 2024; also ICLR 2025 Workshop.
  • TA-MIR: Text Aggregation for Multimodal Feature Representation in Medical Image Registration. Y. Dai, Z. Huang, W. Huang. ISBI 2025.
2024
  • CtxPipe: Context-aware Data Preparation Pipeline Construction for Machine Learning. H. Gao, S. Cai, T. T. A. Dinh, Z. Huang, B. C. Ooi. Proceedings of the ACM on Management of Data (SIGMOD), 2024.
  • Towards Better Text-to-Image Generation Alignment via Attention Modulation. Y. Wu, X. Cao, K. Li, Z. Chen, H. Wang, L. Meng, Z. Huang. ICONIP 2024.
  • Zero-shot Cross-lingual Alignment for Embedding Initialization. X. Ai, Z. Huang. ACL 2024 (Findings).
  • TSGBench: Time Series Generation Benchmark. Y. Ang, Q. Huang, Y. Bao, A. K. H. Tung, Z. Huang. VLDB 2024 (Best Paper Award Nomination).
  • TSGAssist: An Interactive Assistant Harnessing LLMs and RAG for Time Series Generation Recommendations and Benchmarking. Y. Ang, Y. Bao, Q. Huang, A. K. H. Tung, Z. Huang. VLDB 2024 (Demo).
  • PhishDecloaker: Detecting CAPTCHA-cloaked Phishing Websites via Hybrid Vision-based Interactive Models. X. Teoh, Y. Lin, R. Liu, Z. Huang, J. S. Dong. USENIX Security 2024.
  • Less Defined Knowledge and More True Alarms: Reference-based Phishing Detection without a Pre-defined Reference List. R. Liu, Y. Lin, X. Teoh, G. Liu, Z. Huang, J. S. Dong. USENIX Security 2024.
  • EADS: An Early Anomaly Detection System for Sensor-based Multivariate Time Series. Y. Ang, Q. Huang, A. K. H. Tung, Z. Huang. ICDE 2024 (Demo).
  • Multi-Prompts Learning with Cross-Model Alignment for Attribute-based Person Re-Identification. Y. Zhai, Y. Zeng, Z. Huang, Z. Qin, X. Jin, D. Cao. AAAI 2024.