Publications

HeurEvo: Agentic Evolution of Hybrid Solver-Augmented Heuristics for Time-Critical Mathematical Optimization

Feijie Wu, Hugo Barbalho, Konstantina Mellou, Marco Molinaro, Jing Gao, Ishai Menache, Xinzhi Zhang, Sirui Li

arXiv Preprint 2026, arXiv:2609.36303.

The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems

Xiaoze Liu, Ruowang Zhang, Weichen Yu, Siheng Xiong, Liu He, Feijie Wu, Hoin Jung, Matt Fredrikson, Xiaoqian Wang, Jing Gao

arXiv Preprint 2026, arXiv:2602.15382.

Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering

Feijie Wu, Zitao Li, Fei Wei, Yaliang Li, Bolin Ding, Jing Gao

arXiv Preprint 2025, arXiv:2501.07813.

On the Convergence of Quantized Parallel Restarted SGD for Central Server Free Distributed Training

Feijie Wu, Shiqi He, Yutong Yang, Haozhao Wang, Zhihao Qu, Song Guo, Weihua Zhuang

arXiv Preprint 2020, arXiv:2004.09125.

PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning

Feijie Wu, Weiwu Zhu, Yuxiang Zhang, Soumya Chatterjee, Jiarong Zhu, Fan Mo, Rong Luo, Jing Gao

Advances in Neural Information Processing Systems (NeurIPS) 2026.

Acceptance rate: 7900/30709=25.7%

Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns

Shiqi He, Yue Cui, Feijie Wu, Xinyu Ma, Jiaheng Lu, Yaliang Li, Bolin Ding, Mosharaf Chowdhury

Advances in Neural Information Processing Systems (NeurIPS) 2026.

Acceptance rate: 7900/30709=25.7%

Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Masking

Xingchen Wang*, Feijie Wu*, Chenglin Miao, Tianchun Li, Haoyu Hu, Qiming Cao, Jing Gao, Lu Su

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2026.

Acceptance rate: 20% (research track - August cycle)

Oral Presentation

SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning

Tianyang Xu*, Xiaoze Liu*, Feijie Wu, Xiaoqian Wang, Jing Gao

Conference on Language Modeling (COLM) 2025. [Code]

Acceptance rate: 418/1305=32%

Towards Federated RLHF with Aggregated Client Preference for LLMs

Feijie Wu, Xiaoze Liu, Haoyu Wang, Xingchen Wang, Lu Su, Jing Gao

International Conference on Learning Representations (ICLR) 2025. [Code]

Acceptance rate: 32.08%

FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction

Feijie Wu, Xingchen Wang, Yaqing Wang, Tianci Liu, Lu Su, Jing Gao

Advances in Neural Information Processing Systems (NeurIPS) 2024. [Code]

Acceptance rate: 25.8%

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation

Xiaoze Liu, Ting Sun, Tianyang Xu, Feijie Wu, Cunxiang Wang, Xiaoqian Wang, Jing Gao

Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024. [Code]

Towards Efficient Heterogeneous Multi-Modal Federated Learning

Xingchen Wang, Haoyu Wang, Feijie Wu, Tianci Liu, Qiming Cao, Lu Su

ACM Conference on Embedded Networked Sensor Systems (Sensys) 2024.

Acceptance rate: 58/313=18.5%

FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model

Feijie Wu, Zitao Li, Yaliang Li, Bolin Ding, Jing Gao

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2024. [Code]

Acceptance rate: 20% (research track)

Towards Poisoning Fair Representations

Tianci Liu, Haoyu Wang, Feijie Wu, Hengtong Zhang, Pan Li, Lu Su, Jing Gao

International Conference on Learning Representations (ICLR) 2024.

Acceptance rate: 31%

Anchor Sampling for Federated Learning with Partial Client Participation

Feijie Wu, Song Guo, Zhihao Qu, Shiqi He, Ziming Liu, Jing Gao

International Conference on Machine Learning (ICML) 2023. [Code]

Acceptance rate: 1827/6538=28%

GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning

Shiqi He, Qifan Yan, Feijie Wu, Lanjun Wang, Mathias Lécuyer, Ivan Beschastnikh

Annual Conference on Machine Learning and Systems (MLSys) 2023. [Code]

Acceptance rate: 22%

Macular: a Multi-Task Adversarial Framework for Cross-Lingual Natural Language Understanding

Haoyu Wang, Yaqing Wang, Feijie Wu, Hongfei Xue, Jing Gao

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2023.

Acceptance rate: 184/725=25% (ADS track)

Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression

Feijie Wu*, Shiqi He*, Song Guo, Zhihao Qu, Haozhao Wang, Weihua Zhuang, Jie Zhang

ACM/IEEE Design Automation Conference (DAC) 2022.

Acceptance rate: 23%

Parameterized Knowledge Transfer for Personalized Federated Learning

Jie Zhang, Song Guo, Xiaosong Ma, Haozhao Wang, Wenchao Xu, Feijie Wu

Advances in Neural Information Processing Systems (NeurIPS) 2021.

Acceptance rate: 2344/9122=26%

Infinity Battle: A Glance at How Blockchain Techniques Serve in a Serverless Gaming System

Feijie Wu, Ho Yin Yuen, Henry C.B. Chan, Victor C.M. Leung, Wei Cai

ACM International Conference on Multimedia (MM) 2020. [Code]

Proof-of-Play: A Novel Consensus Model for Blockchain-Based Peer-to-Peer Gaming System

Ho Yin Yuen, Feijie Wu, Wei Cai, Henry C.B. Chan, Qiao Yan, Victor C.M. Leung

ACM International Symposium on Blockchain and Secure Critical Infrastructure (BSCI) 2019.

Acceptance rate: 12/44=27%

Best Student Paper Award

Tree Learning: Towards Promoting Coordination in Scalable Multi-Client Training Acceleration

Tao Guo, Song Guo, Feijie Wu, Wenchao Xu, Jiewei Zhang, Qihua Zhou, Quan Chen, Weihua Zhuang

IEEE Transactions on Mobile Computing (TMC) 2024, vol. 23, no. 3.

Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs

Xiaoze Liu, Feijie Wu, Tianyang Xu, Zhuo Chen, Yichi Zhang, Xiaoqian Wang, Jing Gao

IEEE Data Engineering Bulletin 2024, vol. 47, no. 4. [Code]

From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization

Feijie Wu, Song Guo, Haozhao Wang, Haobo Zhang, Zhihao Qu, Jie Zhang, Ziming Liu

IEEE Transactions on Parallel and Distributed Systems (TPDS) 2023, vol. 34, no. 5.

Facilitating Serverless Match-Based Online Games with Novel Blockchain Technologies

Feijie Wu, Ho Yin Yuen, Henry C. B. Chan, Victor C. M. Leung, Wei Cai

ACM Transactions on Internet Technology (TOIT) 2023, vol. 23, no. 1.