Tandem: Serving Hybrid Linear-Attention GUI Agents on Mobile NPUs
Zhuomin Chen, Jingchao Ni, Xu Zheng, Yong Chen, Mo Sha, Wei Cheng, Dongsheng Luo.
I am a Ph.D. Candidate in Computer Science at Florida International University, working on explainable and trustworthy AI. My research develops faithful explanation and evaluation methods for graph neural networks and time-series models, with recent work extending to LLM agents and efficient on-device AI. My work has appeared in TPAMI, NeurIPS, ICML, ICLR, AAAI, and KDD.
- faithful explanation methods for graph neural networks
- robust evaluation frameworks for explainability
- time-series explanation, forecasting, and reasoning
- reliable LLM agents and efficient on-device AI
Recent News
- Oct. 2026 Received the NeurIPS 2026 Financial Assistance Award.
- Oct. 2026 One paper accepted to NeurIPS 2026.
- May. 2026 One paper accepted to KDD 2026 AI4Sciences Track.
- Apr. 2026 One paper accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, IF: 20.4).
- Nov. 2025 One paper accepted to AAAI 2026.
Preprints
Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability
Zhuomin Chen, Jingchao Ni, Xu Zheng, Janki Bhimani, Mo Sha, Wei Cheng, Dongsheng Luo.
Towards A Unified Information Bottleneck Framework for Time Series Explanations
Xu Zheng, Zichuan Liu, Zhuomin Chen, Mayur Akewar, Janki Bhimani, Jason Liu, Mo Sha, Jingchao Ni, Wei Cheng, Dongsheng Luo.
Where Does Knowledge Live? Representational, Causal, and Editable Localization in Language Models: A Survey
Zhuomin Chen, Gabriel Lucchesi, Qingkai Dong, Zhenyu Xu, Xu Zheng, Yong Chen, Mo Sha, Wei Cheng, Jingchao Ni, Dongsheng Luo.
Information Bottleneck Learning for Faithful Time Series Forecasting Explanations
Xu Zheng, Wei Cheng, Zhuomin Chen, Mo Sha, Jingchao Ni, Dongsheng Luo.
Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
Xu Zheng, Zhuomin Chen, Chaohao Lin, Hua Wei, Haifeng Chen, Wei Cheng, Dongsheng Luo.
Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs
Xu Zheng, Chaohao Lin, Zhuomin Chen, Weijieying Ren, Haifeng Chen, Wei Cheng, Dongsheng Luo.
DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL
Esteban Schafir, Xu Zheng, Hojat Allah Salehi, Zhuomin Chen, Mo Sha, Wei Cheng, Dongsheng Luo.
From Signals to Semantics: A Survey on Time Series Explainability through a Human-Cognitive Lens
Zhuomin Chen, Gabriel Lucchesi, Qingkai Dong, Xu Zheng, Dongjin Song, Qingsong Wen, Wei Cheng, Jingchao Ni, Dongsheng Luo.
Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework
Xu Zheng, Zhuomin Chen, Esteban Schafir, Sipeng Chen, Hojat Allah Salehi, Haifeng Chen, Farhad Shirani, Mo Sha, Wei Cheng, Dongsheng Luo.
Selected Publications
Robust Surrogate Modeling for Explainable Graph Neural Networks
Zhuomin Chen, Jingchao Ni, Hojat Allah Salehi, Xu Zheng, Dongsheng Luo.
Addressing Structural Distribution Shift in Explanations for Graph Neural Networks
Zhuomin Chen, Hojat Allah Salehi, Esteban Schafir, Xu Zheng, Jiaxing Zhang, Hua Wei, Jingchao Ni, Farhad Shirani, Dongsheng Luo.
Uncovering Insights of Compound Flooding with Data-Driven AI
Xu Zheng, Chaohao Lin, Sipeng Chen, Zhuomin Chen, Jimeng Shi, Jayantha Obeysekera, Jingchao Ni, Wei Cheng, Jason Liu, Dongsheng Luo.
Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning
Zhuomin Chen, Jingchao Ni, Hojat Allah Salehi, Xu Zheng, Esteban Schafir, Farhad Shirani, Dongsheng Luo.
F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI
Xu Zheng, Farhad Shirani, Zhuomin Chen, Chaohao Lin, Wei Cheng, Wenbo Guo, Dongsheng Luo.
Generating In-Distribution Proxy Graphs for Explainable Graph Neural Networks
Zhuomin Chen, Jiaxing Zhang, Jingchao Ni, Xiaoting Li, Yuchen Bian, Md Mezbahul Islam, Ananda Mohan Mondal, Hua Wei, Dongsheng Luo.
RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
Jiaxing Zhang, Zhuomin Chen, Hao Mei, Dongsheng Luo, Hua Wei.
TimeX++: Learning Time-Series Explanations with Information Bottleneck
Zichuan Liu, Tianchun Wang, Jimeng Shi, Xu Zheng, Zhuomin Chen, Lei Song, Wenqian Dong, Jayantha Obeysekera, Farhad Shirani, Dongsheng Luo.
Professional Service
Conference Reviewer
ICML (2025, 2026), NeurIPS (2025, 2026), ICLR (2026, 2027), KDD (2026, 2027), WWW (2025, 2026), AAAI (2026, 2027), ICDM (2023, 2024), PAKDD (2024), SMC (2026).
Journal Reviewer
TPAMI, TKDE, TAI, TKDD, TMI, TBD, TNNLS, Expert Systems, and T-IFS.
Program Committee
ICML 2025, AAAI 2026, and WWW 2026.
Teaching Experience
Teaching Assistant, Florida International University
- Course: Discrete Structures (2024 Spring, 2024 Summer)
- Course: Computer Data Analysis (2023 Fall)
Awards
- NeurIPS Financial Assistance Award, 2026
- NSF Travel Award, SIAM SDM Doctoral Forum, 2024
- Provincial Outstanding Graduate
- First- and Second-Class Scholarships, Qingdao University and Taiyuan University of Technology
Personal note
Outside of research, I enjoy going to concerts, watching the WNBA (currently rooting for the Dallas Wings because I'm a fan of Paige Bueckers, Azzi Fudd, and Li Yueru) and TV shows, and traveling (especially hiking in U.S. national parks). I am always happy to connect with people interested in machine learning, explainability, and trustworthy AI.