About Me

Hi, I'm Jiaqing! I am a research assistant at the Shanghai AI Lab AI for Science Center. I received my M.Sc. in Computer Science from ETH Zurich in 2025, and my B.Eng. in Electronics and Computer Science from the University of Edinburgh in 2022. I will start my Ph.D. in Computer Science at Fudan University in September 2026.

My research focuses on AI for physical sciences, generative models (flow matching and diffusion models), graph neural networks and graph transformers, and their applications to chemistry, spectroscopy, and molecular modeling. You can see my papers on Google Scholar or download my CV.

If you want to reach me, email me at godxie.steven@gmail.com.

News

• [2026/04] We released GeoBA in May.
• [2026/04] We released ChemClaw, an agentic framework for chemistry with modular skills.
• [2026/03] Two second-authored papers are accepted by CVPR 2026 (One Main, One Findings).
• [2026/02] We launched NMRGym and NMRTrans for better NMR structure elucidation.
• [2025/11] First co-authored paper GraphPEBench is accepted by KDD 2026.
• [2025/11] One paper DeepResearchArena is accepted by AAAI 2026.
• [2025/10] First authored paper QCBench is published in JCIM 2025.
• [2025/05] First authored paper DeepProtein is published in Bioinformatics 2025.

Education & Experience

• Shanghai AI Lab — Assistant Researcher, AI for Science Center (2025 — Present)
• Fudan University — Ph.D., Computer Science (Sept 2026 - Current)
• ETH Zurich — M.Sc., Computer Science (2022 - 2025)
• University of Edinburgh — B.Eng., Electronics and Computer Science (2019 - 2022)

Publications

^‡ indicates equal contribution.

Graph Neural Networks

• Scaling Learnable Laplacian Positional Encodings with Random-Probe Krylov Methods
  Jiaqing Xie
  To be released
• Benchmarking Positional Encodings for GNNs and Graph Transformers
  Florian Grotschla^‡, Jiaqing Xie^‡ and Roger Wattenhofer
  SIGKDD 2026
  Paper · Code

AI for Physical Science

• Antibody Design via On-Policy Self-Distillation
  Zhuo Yang, Jiaying He, Jiaqing Xie et al.
  To be released
• SpectraFlow: Physics-guided Flow Matching for IR-Raman Spectral Interconversion
  Jiaqing Xie, Zhuo Yang, Ben Gao, Shuaike Shen, Tianfan Fu, Yuqiang Li
  To be released
• NMRGym: A Comprehensive Benchmark for Nuclear Magnetic Resonance Based Molecular Structure Elucidation
  Zheng Fang, Chen Yang, Hai-tao Yu, Haoming Luo, Haitao He, Jiaqing Xie, Zhuo Yang, Yuqiang Li, Jun Xia
  SIGKDD 2026
  Paper · Code
• NMRTrans: Structure Elucidation from Experimental NMR Spectra via Set Transformers
  Liujia Yang^‡, Zhuo Yang^‡, Jiaqing Xie^‡, Yubin Wang^‡, Ben Gao, Tianfan Fu, Xingjian Wei, Jiaxing Sun, Jiang Wu, Conghui He, Yuqiang Li, Qinying Gu
  SIGKDD 2026
  Paper · Code
• SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy
  Zhuo Yang^‡, Jiaqing Xie^‡, Shuaike Shen, Daolang Wang, Yeyun Chen, Ben Gao, Shuzhou Sun, Biqing Qi, Dongzhan Zhou, Lei Bai, Linjiang Chen, Shufei Zhang, Jun Jiang, Tianfan Fu, and Yuqiang Li
  SIGKDD 2026
  Paper · Code
• PolyReal: A Benchmark for Real-World Polymer Science Workflows
  Wanhao Liu^‡, Weida Wang^‡, Jiaqing Xie, Suorong Yang, Jue Wang, Benteng Chen, Guangtao Mei, Zonglin Yang, Shufei Zhang, Yuchun Mo, Lang Cheng, Jin Zeng, Houqiang Li, Wanli Ouyang, Yuqiang Li
  CVPR 2026 Findings
  Paper · Code
• DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning
  Jiaqing Xie, Yuqiang Li and Tianfan Fu
  Bioinformatics 2025
  Paper · Code

Large Language Models

• R2-Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection
  Shuaike Shen^‡, Ke Liu^‡, Jiaqing Xie, Shangde Gao, Chunhua Shen, Ge Liu, Mireia Crispin-Ortuzar, Shangqi Gao
  CVPR 2026 (Best Paper Candidate)
  Paper · Code
• QCBench: Evaluating Large Language Models on Domain-Specific Quantitative Chemistry
  Jiaqing Xie‡, Weida Wang‡, Ben Gao‡, Zhuo Yang, Haiyuan Wan, Shufei Zhang, Tianfan Fu, and Yuqiang Li
  JCIM 2025
  Paper · Code
• Deep Research Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
  Haiyuan Wan, Chen Yang, Junchi Yu, Meiqi Tu, Jiaxuan Lu, Di Yu, Jianbao Cao, Ben Gao, Jiaqing Xie, Aoran Wang, Wenlong Zhang, Philip Torr, Dongzhan Zhou
  AAAI 2026
  Paper · Code

Technical Report

• MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization
  Zhuo Yang^‡, Yeyun Chen^‡, Jiaqing Xie, Ben Gao, Shuaike Shen, Wanhao Liu, Liujia Yang, Beilun Wang, Tianfan Fu, Yuqiang Li
  Under Review, Arxiv
  Paper · Code
• When to Use SAEs for LLM Steering: A Comparative Study with Mean Activation Differences
  Jiaqing Xie
  Under Review, Arxiv
  Paper · Code

Under Review

• GeoBA: Geometry-Biased Attention for Molecular Property Prediction
  Jiaqing Xie, Ziheng Chi, Zhuo Yang
  Under Review, Arxiv
• SkillsInjector: Dynamic Skill Context Construction for LLM Agents
  Yanchao Li, Wanhao Liu, Ben Gao, Jiaqing Xie, Zhehong Ai, Na Zou, Yuqiang Li, Tianfan Fu
  Under Review, Arxiv
  Paper
• OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields
  Wanhao Liu^‡, Jiaqing Xie^‡, Qian Tan, Weida Wang, Jue Wang, Ran Sun, Zhuo Yang, Lei Bai, TianFan Fu, Lu Chen, Xin Chen, Yuqiang Li
  Under Review, Arxiv
  Paper
• SpecMol: A Unified Framework for Spectroscopy-Grounded Molecular Modeling and Evaluation
  Shuaike Shen^‡, Jiaqing Xie^‡, Zhuo Yang, Antong Zhang, Shuzhou Sun, Ben Gao, Tianfan Fu, Biqing Qi, Yuqiang Li
  Under Review, Arxiv
  Paper · Code

Personal Info

• Physical: height 183 cm, weight 80 kg.
• Running (PB): 50 m 6.5 s; 1000 m 3′22″; 5000 m 27′30″; 10000 m 55′30″.
• Weiqi (Go): Chinese Weiqi Association amateur 1 dan (2008).
• Singing: 300+ fans.
• Zhihu: 2800 followers — P等于NP.
• Codeforces: 1200.

Academic Services (Reviewer)

• 2025: ACL, CVPR, EMNLP, ICONIP, NeurIPS
• 2024: ACML, NeurIPS