My name is Jiaqing Xie (谢嘉庆). I am a year-one PhD student in Computer Science at Fudan University. I work on graph and flow models, in theory and in practice.

My research interests include spectral methods, graph neural networks, geometric deep learning, flow-based generative models, and AI for scientific workflows. I am interested in developing machine learning methods that connect graph structure, symmetry, and physical or chemical inductive bias.

I received my M.Sc. in Computer Science from ETH Zurich, where I followed the Theoretical Computer Science track. Before that, I received my B.Eng. degree from the University of Edinburgh.

Forthcoming

Jiaqing Xie, Yuxin Wang, and Xipeng Qiu. GSF-χ: Global Stereochemical Fields for Chiral Graph Transformers. To be released soon.

Jiaqing Xie, Yanchao Li, Zhuo Yang, Tianfan Fu, and Yuxin Wang. Equivariant Neural Primal–Dual Assignment for Maximum Common Edge Subgraphs. To be released soon.

Jiaqing Xie, Yanchao Li, Ben Gao, Wanhao Liu, and Tianfan Fu. Fixed-Density Transport Lifting: Riemannian Energy Matching for Generative Sampling.

Jiaqing Xie, Zhuo Yang, Ben Gao, Shuaike Shen, Tianfan Fu, and Yuqiang Li. SpectraFlow: Peak-Aware Flow Matching for Bidirectional Infrared–Raman Spectral Translation and Molecular Property Prediction. [code]

2026

Jiaqing Xie and Yuxin Wang. Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces. [arXiv]

[AAAI 2026] Haiyuan Wan, Chen Yang, Jing Yu, Ming Tu, Jing Lu, Dong Yu, Jia Cao, Ben Gao, Jiaqing Xie, Ao Wang, et al. Deep Research Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks.

[KDD 2026, co-first] Florian Grotschla^*, Jiaqing Xie^*, and Roger Wattenhofer. Benchmarking Positional Encodings for GNNs and Graph Transformers. [arXiv] [code]

[KDD 2026, co-first] Zhuo Yang^*, Jiaqing Xie^*, Shuaike Shen, Dong Wang, Yeyun Chen, Ben Gao, Shuzhou Sun, Biqing Qi, Dong Zhou, and Yuqiang Li. SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy. [arXiv]

[KDD 2026] Zhen Fang, Chen Yang, Hao Yu, Haoming Luo, Haitao He, Jiaqing Xie, Zhuo Yang, Yuqiang Li, and Jun Xia. NMRGym: A Comprehensive Benchmark for Nuclear Magnetic Resonance Based Molecular Structure Elucidation. [arXiv] [code]

Yanchao Li, Wanhao Liu, Ben Gao, Jiaqing Xie, Zhehong Ai, Na Zou, Yuqiang Li, and Tianfan Fu. SkillsInjector: Dynamic Skill Context Construction for LLM Agents. [arXiv]

[KDD 2026, co-first] Liujia Yang^*, Zhuo Yang^*, Jiaqing Xie^*, Yubin Wang^*, Ben Gao, Tianfan Fu, Xingjian Wei, Jiaxing Sun, Jiang Wu, Conghui He, Yuqiang Li, and Qinying Gu. NMRTrans: Structure Elucidation from Experimental NMR Spectra via Set Transformers. [arXiv] [code]

[CVPR 2026] Wanhao Liu, Weida Wang, Jiaqing Xie, Suorong Yang, Jue Wang, Benteng Chen, Guangtao Mei, Zhuo Yang, Shufei Zhang, Tianfan Fu, and Yuqiang Li. PolyReal: A Benchmark for Real-World Polymer Science Workflows. [arXiv] [code]

Wanhao Liu^*, Jiaqing Xie^*, Qian Tan, Weida Wang, Jue Wang, Ran Sun, Zhuo Yang, Wanli Ouyang, Lei Bai, Tianfan Fu, Lu Chen, Xin Chen, and Yuqiang Li. OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields. [arXiv] [code]

[CVPR 2026] Shuaike Shen, Ke Liu, Jiaqing Xie, Shangde Gao, Chunhua Shen, Ge Liu, Mireia Crispin-Ortuzar, and Shangqi Gao. R²-Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection. [arXiv] [code]

Yanchao Li, Wanhao Liu, Jiaqing Xie, Ben Gao, Yuxin Wang, Tianfan Fu, and Yuqiang Li. Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains. [arXiv] [code]

Yanchao Li, Jiaqing Xie, Ben Gao, Wanhao Liu, Yuxin Wang, Tsz Yin Tsui, Jing Liu, Yuqiang Li, and Tianfan Fu. Disagree to Accelerate: Closing the Loop on Diffusion Feature Forecasts. [arXiv] [code]

Zhuo Yang, Jia He, Jiaqing Xie, Dong Wang, Xipeng Qiu, Yuxin Wang, Tianfan Fu, and Beilun Wang. ABOPD: Antibody CDR Design via On-Policy Distillation. [arXiv]

Yanchao Li, Shuaike Shen, Jiaqing Xie, Zhuo Yang, Antong Zhang, Shuzhou Sun, Ben Gao, Tianfan Fu, Biqing Qi, and Yuqiang Li. SpecMol: A Unified Framework for Spectroscopy-Grounded Molecular Modeling and Evaluation.

2025

[JCIM 2025] Jiaqing Xie, Weida Wang, Ben Gao, Zhuo Yang, Haiyuan Wan, Shufei Zhang, Tianfan Fu, and Yuqiang Li. QCBench: Evaluating Large Language Models on Domain-Specific Quantitative Chemistry. [arXiv] [code] [dataset]

[Bioinformatics 2025] Jiaqing Xie, Yuqiang Li, and Tianfan Fu. DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning. [code]

Shuaike Shen^*, Jiaqing Xie^*, Zhuo Yang, Antong Zhang, Shuzhou Sun, Ben Gao, Tianfan Fu, Biqing Qi, and Yuqiang Li. SpecMol: A Spectroscopy-Grounded Foundation Model for Multi-Task Molecular Learning. [arXiv] [code]

Jiaqing Xie. A Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering. [arXiv]

Zhuo Yang, Yeyun Chen, Jiaqing Xie, Ben Gao, Shuaike Shen, Wanhao Liu, Liujia Yang, Beilun Wang, Tianfan Fu, and Yuqiang Li. MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization. [arXiv] [code]

2024

Yuxin Wang, Xiannian Hu, Jiaqing Xie, Zhangyue Yang, Yunhua Zhou, and Xipeng Qiu. Graph Structure Learning via Lottery Hypothesis at Scale.

^* Equal contribution (2025–present).

Reviewer

• NeurIPS (2024, 2025)
• Journal of Chemical Information and Modeling (JCIM)