Publications

2026

  1. MindOS: A Shared Mind for Human-agent Coevolution
    Tianfu Wang, Nicholas Jing Yuan, and Hui Xiong
    Website Code
  2. Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities
    Tianfu Wang, Zhezheng Hao, Xilin Xia, Lixin Liu, Mengkang Hu, Hongzhang Liu,
    4 more authorsXi Chen, Ziyan Liu, Xiankun Lin, Weijia Zhang
    , Nicholas Jing Yuan, and Hui Xiong
    Website PDF Code
  3. Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer
    Tianfu Wang, Zhezheng Hao, Yin Wu, Wei Wu, Qiang Lin, Hande Dong, Nicholas Jing Yuan, and Hui Xiong
    Website PDF Code
  4. NeurIPS
    EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
    Tianfu Wang, Leilei Ding, Ziyang Tao, Yi Zhan, Zhiyuan Ma, Wei Wu,
    7 more authorsYuxuan Lei, Junyang Wang, Yizhao Xu, Yin Wu, Zhengyu Hu, Hongyuan Zhu, Nicholas Jing Yuan
    , Yanyong Zhang, and Hui Xiong
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
    Website PDF Code
  5. ICLR
    Virne: A Comprehensive Benchmark for RL-based Network Resource Allocation in NFV
    Tianfu Wang, Liwei Deng, Xi Chen, Junyang Wang, Huiguo He, Zhengyu Hu,
    2 more authorsWei Wu, Leilei Ding
    , Qilin Fan, and Hui Xiong
    In International Conference on Learning Representations (ICLR), 2026
    Website PDF Code
  6. TR
    Kimi K3: Open Frontier Intelligence
    Kimi Team (Tianfu Wang is a co-author)
    Website PDF Code
  7. ICML
    A Computational Framework for Evaluating Human-likeness in LLMs’ Open-ended Human Behaviors
    Yuxuan Lei, Jianxun Lian, Defu Lian, Jincenzi Wu, Tianfu Wang, and Xing Xie
    In International Conference on Machine Learning (ICML), 2026
    Website PDF
  8. ACL
    Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
    Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu,
    2 more authorsYan Gao, Yi Wu
    , Yao Hu, and Hui Xiong
    In Annual Meeting of the Association for Computational Linguistics (ACL Main Conference), 2026
    PDF Code
  9. EMNLP·F
    Unsupervised Post-Training of Foundation Models: A Survey
    Yijie Xu, Qianyi Cai, Huizai Yao, Yili Wang, Tianfu Wang, Cehao Yang,
    4 more authorsXingbo Yao, Zhiyu Guo, Aiwei Liu, Xuming Hu
    , Weiyu Guo, and Hui Xiong
    In Findings of the Association for Computational Linguistics: EMNLP 2026, 2026
    PDF
  10. NeurIPS
    Population-Aligned Persona Generation for LLM-based Social Simulation
    Zhengyu Hu, Jianxun Lian, Zheyuan Xiao, Max Xiong, Tianfu Wang, Teng Xiao,
    5 more authorsYuxuan Lei, Fengqing Jiang, Kaize Ding, Ziang Xiao, Nicholas Jing Yuan
    , Xing Xie, and Radha Poovendran
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
    Website PDF
  11. NeurIPS
    Machine Unlearning in Diffusion LLMs
    Yili Wang, Yijie Xu, Lu Dai, Tairan Huang, Qianyi Cai, Huizai Yao, Tianfu Wang, and Hui Xiong
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
    Website
  12. NeurIPS
    Two Drifts, One Principle: Conflict-Aware Spectral Consolidation for Multimodal Continual Learning
    Haiyi Zhang, Qianyi Cai, Hanqing Wang, Zilin Wang, Xinyue Di, Yijie Xu,
    2 more authorsYili Wang, Tianfu Wang
    , Yifan Han, and Hui Xiong
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
    Website
  13. Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
    Zhezheng Hao*, Tianfu Wang*, Huanshuo Dong, Ziyan Liu, Hong Wang, Xiankun Lin,
    2 more authorsQiang Lin, Can Wang
    , Hande Dong, and Jiawei Chen
    PDF Code
  14. KDD
    HumanLLM: Towards Personalized Understanding and Simulation of Human Nature
    Yuxuan Lei, Tianfu Wang, Jianxun Lian, Zhengyu Hu, Defu Lian, and Xing Xie
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026
    PDF Code
  15. SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice
    Tianfu Wang, Max Xiong, Yuxuan Lei, Jianxun Lian, Hongyuan Zhu, Zhengyu Hu,
    4 more authorsLinxiao Gong, Dapeng Hu, Xiaofang Li, Peiting Tsai
    , Nicholas Jing Yuan, and Qi Zhang
    Website Demo PDF Code
  16. CVPR·F
    AlignFL: Adaptive Learning and Intelligent Generation of Networks for Federated Learning
    Qilin Xiang, Qilin Fan, Xinrui Li, Tianfu Wang, Shuting Qiu, and Yue Niu
    In Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026
    PDF
  17. CVPR·F
    Beyond Voxel 3D Editing : Learning from 3D Masks and Self-Constructed Data
    Yizhao Xu, Hongyuan Zhu, Caiyun Liu, Tianfu Wang, Keyu Chen, Sicheng Xu,
    1 more authorJiaolong Yang
    , Nicholas Jing Yuan, and Qi Zhang
    In Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026
    PDF
  18. ICDE
    TopFGL: A Topology-Aware and Distribution-Agnostic Federated Learning Framework Tackling Topological Heterogeneity on Graph Data
    Junyang Wang, Lan Zhang, Yihang Cheng, Mu Yuan, Tianfu Wang, Zhihui Fu, and Jun Wang
    In IEEE International Conference on Data Engineering (ICDE), 2026
    Website

2025

  1. WWW
    LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System
    Tianfu Wang, Yi Zhan, Jianxun Lian, Zhengyu Hu, Nicholas Jing Yuan, Qi Zhang, Xing Xie, and Hui Xiong
    In ACM Web Conference (WWW), 2025
    Oral Presentation
    Website Demo PDF Code Poster Slides
  2. ICMLW
    Towards Constraint-aware Learning for Resource Allocation in NFV Networks
    Tianfu Wang, Long Yang, Chao Wang, Chuan Qin, Liwei Deng, Li Shen, and Hui Xiong
    In ICML 2025 Workshop on Machine Learning for Wireless Communication and Networks (ML4Wireless), 2025
    Best Paper Award
    PDF Code
  3. VLDB
    MILLION: A General Multi-Objective Framework with Controllable Risk for Portfolio Management
    Liwei Deng*, Tianfu Wang*, Yan Zhao, and Kai Zheng
    In International Conference on Very Large Data Bases (VLDB), 2025
    PDF Code
  4. NeurIPS
    Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
    Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhenyu Chen,
    2 more authorsJianxun Lian, Nicholas Jing Yuan
    , Kaize Ding, and Hui Xiong
    In Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
    PDF
  5. VLDB
    Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search
    Liwei Deng, Penghao Chen, Ximu Zeng, Tianfu Wang, Yan Zhao, and Kai Zheng
    In International Conference on Very Large Data Bases (VLDB), 2025
    PDF Code
  6. IJCAI
    CoderAgent: Simulating Student Behavior for Personalized Programming Learning with Large Language Models
    Yi Zhan, Qi Liu, Weibo Gao, Zheng Zhang, Tianfu Wang, Zhenya Huang, Junyu Lu, and Shuanghong Shen
    In International Joint Conference on Artificial Intelligence (IJCAI), 2025
    PDF Code
  7. ICDE
    Exact and Efficient Similar Subtrajectory Search: Integrating Constraints and Simplification
    Liwei Deng, Fei Wang, Tianfu Wang, Yan Zhao, Yuyang Xia, and Kai Zheng
    In IEEE International Conference on Data Engineering (ICDE), 2025
    PDF Code
  8. EMNLP
    TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
    Wei Wu, Zhuoshi Pan, Chao Wang, Liyi Chen, Yunchu Bai, Tianfu Wang,
    1 more authorKun Fu
    , Zheng Wang, and Hui Xiong
    In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
    PDF
  9. EMNLP
    Explaining Length Bias in LLM-Based Preference Evaluations
    Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhenyu Chen,
    2 more authorsJianxun Lian, Nicholas Jing Yuan
    , Kaize Ding, and Hui Xiong
    In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
    PDF
  10. JSA
    GNN-based Deep Reinforcement Learning for Computation Task Scheduling in Autonomous Multi-Robot Systems
    Wen Gao, Zhiwen Yu, Tianfu Wang, Liang Wang, Helei Cui, Bin Guo, and Hui Xiong
    Journal of Systems Architecture: Embedded Software Design (JSA), 2025
    PDF
  11. TGCN
    IKENGA: Infeasibility Knowledge Enhanced Genetic Algorithm for Virtual Network Embedding
    Fei Wang, Qilin Fan, Tianfu Wang, Xu Zhang, Xiuhua Li, and Hao Yin
    IEEE Transactions on Green Communications and Networking (TGCN), 2025
    PDF

2024

  1. KDD
    COMET: NFT Price Prediction with Wallet Profiling
    Tianfu Wang, Liwei Deng, Chao Wang, Jianxun Lian, Yue Yan, Nicholas Jing Yuan, Qi Zhang, and Hui Xiong
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024
    PDF Code Poster Slides
  2. IJCAI
    FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource Allocation
    Tianfu Wang, Qilin Fan, Chao Wang, Long Yang, Leilei Ding, Nicholas Jing Yuan, and Hui Xiong
    In International Joint Conference on Artificial Intelligence (IJCAI), 2024
    PDF Code Poster Slides
  3. IJCAI
    DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
    Leilei Ding, Dazhong Shen, Chao Wang, Tianfu Wang, Le Zhang, and Yanyong Zhang
    In International Joint Conference on Artificial Intelligence (IJCAI), 2024
    PDF

2023

  1. TSC
    Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
    Tianfu Wang, Shen Li, Qilin Fan, Tong Xu, Tongliang Liu, and Hui Xiong
    IEEE Transaction on Services Computing (TSC), 2023
    PDF Code
  2. MM
    Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement Learning
    Huiguo He, Tianfu Wang, Huan Yang, Jianlong Fu, Nicholas Jing Yuan, Jian Yin, Hongyang Chao, and Qi Zhang
    In ACM International Conference on Multimedia (MM), 2023
    PDF
  3. AES
    GAT-IL: A Service Function Chain Deployment Method Based on Graph Attention Network and Imitation Learning
    Qilin Fan, Yue Niu, Hao Yin, Tianfu Wang, Xiuhua Li, and Jinlong Hao
    Acta Electronica Sinica (电子学报), 2023
    PDF

2021

  1. ICC
    DRL-SFCP: Adaptive Service Function Chains Placement with Deep Reinforcement Learning
    Tianfu Wang, Qilin Fan, Xiuhua Li, Xu Zhang, Qingyu Xiong, Shu Fu, and Min Gao
    In IEEE International Conference on Communications (ICC), 2021
    PDF Code