Jiacheng Liu

PhD student · MBZUAI · advised by Zhiqiang Shen.

My research focuses on efficient generative models and agents.

Previously MSc at UCL, advised by Prof. Jun Wang; part-time research intern at Huawei Noah's Ark Lab, London (2023–2024) with Dr. Kun Shao.

Abu Dhabi, UAE

jiacheng.liu [at] mbzuai.ac.ae

✉ email · github · google scholar

publications

in reversed chronological order.

2026

arXiv Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense.
Jiacheng Liu, Yaxin Luo, Jiacheng Cui, Xinyi Shang, Xiaohan Zhao, Zhiqiang Shen. arXiv:2602.09012, 2026. arXiv · code · project

CVPR BiGain: Unified Token Compression for Joint Generation and Classification.
Jiacheng Liu, Shengkun Tang, Jiacheng Cui, Dongkuan Xu, Zhiqiang Shen. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. arXiv · code

arXiv Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems.
Jiacheng Liu, Xiaohan Zhao, Xinyi Shang, Zhiqiang Shen. arXiv:2604.14228, 2026. arXiv · code (787★)

arXiv Exploring 3D Dataset Pruning.
Xiaohan Zhao, Xinyi Shang, Jiacheng Liu, Zhiqiang Shen. arXiv:2603.00651, 2026. arXiv

arXiv From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering.
Xinyi Shang, Yi Tang, Jiacheng Cui, Ahmed Elhagry, Salwa K. Al Khatib, Sondos Mahmoud Bsharat, Jiacheng Liu, Xiaohan Zhao, Jing-Hao Xue, Hao Li, Salman Khan, Zhiqiang Shen. arXiv:2603.20193, 2026. arXiv · code

DMLR Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark.
Sondos Mahmoud Bsharat, Mukul Ranjan, Aidar Myrzakhan, Jiacheng Liu, Bowei Guo, Shengkun Tang, Zhuang Liu, Yuanzhi Li, Zhiqiang Shen. Journal of Data-centric Machine Learning Research (DMLR), 2026. arXiv · code

2025

NeurIPS Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents.
Yaxin Luo, Zhaoyi Li, Jiacheng Liu, Jiacheng Cui, Xiaohan Zhao, Zhiqiang Shen. Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2025. arXiv · code

NeurIPS FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation.
Jiacheng Cui, Xinyue Bi, Yaxin Luo, Xiaohan Zhao, Jiacheng Liu, Zhiqiang Shen. Conference on Neural Information Processing Systems (NeurIPS), 2025. arXiv · code

2024

arXiv Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning.
Filippos Christianos, Georgios Papoudakis, Matthieu Zimmer, Thomas Coste, Zhihao Wu, Jingxuan Chen, Khyati Khandelwal, James Doran, Xidong Feng, Jiacheng Liu, Zheng Xiong, Yicheng Luo, Jianye Hao, Kun Shao, Haitham Bou-Ammar, Jun Wang. arXiv:2312.14878, 2024. arXiv

Work conducted as part-time research intern at Huawei Noah's Ark Lab, London.