Research Area 02
AI Foundations & Learning
Foundation modelsAgentic AIExplainable AIFederated learningGraph learningAI optimization
Overview
xGI develops the foundations of intelligent systems through advances in machine learning, foundation models, and autonomous decision-making. Research explores agentic AI, explainable and trustworthy AI, federated and distributed learning, graph-based learning, and optimization-driven intelligence. These efforts aim to create scalable, adaptive, and reliable AI systems that can operate across diverse real-world environments.
Affiliated Faculties
Affiliated Faculties
Highlighted Publications
- K. Yue, R. Jin, C. Wong, D. Baron, and H. Dai, “Gradient Obfuscation Gives a False Sense of Security in Federated Learning,” 2023 USENIX Security Symposium, Anaheim, CA, Aug. 9-11, 2023.
- “Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization”. Weizhi Gao, Zhichao Hou, Junqi Yin, Feiyi Wang, Linyu Peng, Xiaorui Liu. International Conference on Machine Learning (ICML 2025).
- J. Liu, Z. Peng, D. Xu, and Y. Liu, “Revolutionizing Wireless Modeling and Simulation with Network-Oriented LLMs,” IEEE International Performance Computing and Communications Conference (IPCCC), 2024. (Best Paper Award Runner-up)
- Gajjar, P., & Shah, V. K. (2026). TeleEmbedBench: A Multi-Corpus Embedding Benchmark for RAG in Telecommunications. arXiv preprint arXiv:2604.17778.
- Grainger, Ryan and Paniagua, Thomas and Song, Xi and Cuntoor, Naresh and Lee, Mun Wai and Wu, Tianfu, PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers, CVPR 2023.
- Paniagua, Thomas and Savadikar, Chinmay and Wu, Tianfu, Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian, ICML 2025.
- Gajjar, P., Ojo, E., & Shah, V. K. (2026). TeleResilienceBench: Quantifying Resilience for LLM Reasoning in Telecommunications. arXiv preprint arXiv:2605.09929.
- Xue, Rui and Wu, Tianfu, HarmonyGNNs: Harmonizing Heterophily and Homophily in GNNs via Joint Structural Node Encoding and Self-Supervised Learning, ICLR 2026.
- “Robustness Reprogramming for Representation Learning”. Zhichao Hou, MohamadAli Torkamani, Hamid Krim, Xiaorui Liu. International Conference on Learning Representations (ICLR 2025 Spotlight).
- X. Luo, Z. Li, Z. Peng, M. Chen, and Y. Liu, “Denoising Diffusion Probabilistic Model for Radio Map Estimation in Generative Wireless Networks,” IEEE Transactions on Cognitive Communications and Networking (TCCN), 2025.
- K. Yue, R. Jin, R. Pilgrim, C.-W. Wong, D. Baron, H. Dai, “Neural tangent kernel empowered federated learning,” International Conference on Machine Learning (ICML), Baltimore, 17–23 July 2022.
- Z. Hou, M. Torkamani, H. Krim, X. Liu, ”Robustness Reprogramming for Representation Learning”, ICLR 2025, Singapore.
- Natanzi, S. B. H., Gajja, P., Tang, B., & Shah, V. K. (2026). Advanced AI Service Provisioning in O-RAN through LLM Engine Integration. arXiv preprint arXiv:2605.23809.
- R. Jin, Z. Su, C. Zhong, Z. Zhang, T. Quek, and H. Dai, “Breaking the Communication-Privacy-Accuracy Tradeoff with f-Differential Privacy,” Proc. the 37th International Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, Dec. 10-16, 2023.
- S. Roheda and H. Krim, ”Volterra Neural Networks: A New Perspective on Learning”, Journal of Machine Learning Research, 2024.
- Z. Peng, Y. Liu, G. Li, Z. Yang, M. Chen, D. Xu, and X. Lin, “Generative Artificial Intelligence Models for Emerging Communication Systems: Fundamentals and Challenges,” IEEE Communications Magazine (COMMAG), 2025.
- Z. Zhang, M. Fang, D. Chen, X. Yang, and Y. Liu, “Synergizing AI and Digital Twins for Next Generation Network Optimization, Forecasting, and Security,” IEEE Wireless Communications (WCM), 2025.
- Gajjar, P., & Shah, V. K. (2025). Oransight-2.0: Foundational LLMs for O-RAN. IEEE Transactions on Machine Learning in Communications and Networking.
- H. Yun, E. Chouzenoux, B. Jiang, J.C. Pesquet, H. Krim, ”Geometry via Vision Transformer: Learning by Proximal Updates”, submitted to Signal Processing Journal, 2026 (under review).
- “Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networks”. Sihao Liu, Fangtong Zhou, Xiaorui Liu, Ruozhou Yu, Guoliang Xue. IEEE Transactions on Networking (ToN 2026).
- G. Thompson, K. Yue, C.-W. Wong, and H. Dai, “NTK-DFL: Enhancing decentralized federated learning in heterogeneous settings via neural tangent kernel,” International Conference on Machine Learning (ICML), Vancouver, Canada, 13–19 Jul. 2025.
- Savadikar, Chinmay and Dai, Michelle and Wu, Tianfu, CHEEM: Continual Learning by Reuse, New, Adapt and Skip -- A Hierarchical Exploration-Exploitation Approach, CVPR 2026.
- R. M. Shahroz Khan, P. Li, S. Yun, Z. Wang, S. Nirjon, C.-W. Wong, and T. Chen, “PortLLM: Personalizing evolving large language models with training-free and portable model patches,” International Conference on Learning Representations (ICLR), Singapore, 24–28 Apr. 2025.
- W. Tang, É. Chouzenoux, J.C. Pesquet, and H. Krim, “Deep transform and metric learning network: Wedding deep dictionary learning and neural network,” Neurocomputing, 509: 244-256, 2022.
- M. F. Reza, R. Jin, T. Wu, and H. Dai, “GSBAK: Top-K Geometric Score-based Black-box Attack,” 2025 International Conference on Learning Representations (ICLR), Singapore, Apr. 24-28, 2025.
- C. Zhao, Z. Tan, C.-W. Wong, X. Zhao, T. Chen, and H. Liu, “SCALE: Towards collaborative content analysis in social science with large language model agents and human intervention,” Annual Meeting of the Association for Computational Linguistics (ACL), Vienna, Austria, 27 Jul.–1 Aug. 2025.
- “Harnessing Trust in Directed Graphs: Redefining Robustness of Graph Learning”. Zhichao Hou, Xitong Zhang, Wei Wang, Charu Aggarwal, Xiaorui Liu. ACM Transactions on Knowledge Discovery from Data (TKDD 2026).
- R. Jin and H. Dai, “Noisy SIGNSGD Is More Differentially Private Than You (Might) Think,” 2025 International Conference on Machine Learning (ICML), Vancouver, CA, July 13-19, 2025.
- M. Lee, G. Yu, H. Dai, and G. Y. Li, “Graph Neural Networks Meet Wireless Communications: Motivation, Applications, and Future Directions,” IEEE Wireless Communications, vol. 29, no. 5, pp. 12-19, Oct. 2022.
- W. Liu, X. Zhao, Y. Sun, and C.-W. Wong, “Serving multicultural publics: Assessing the role of dialogic communication and cultural tailoring strategies of GenAI chatbots in government OPRs for disasters,” 28th International Public Relations Research Conference (IPRRC), Orlando, FL, 6–8 Mar. 2025. (Boston University Award for the Top Paper about Public Relations and the Social and Emerging Media)
- N. Yang, S. Wang, Y. Liu, C. Brinton, C. Yin, and M. Chen, “Graph Neural Networks for the Optimization of Collaborative Federated Learning Energy Efficiency,” IEEE Transactions on Mobile Computing (TMC), 2025.
- V. Jebraeeli, B. Jiang, D. Cansever, H. Krim, ”Koopcon: A new approach towards smarter and less complex learning”, Int. Conf. on Image Processing, 2024, Abu Dhabi.
- “Efficient End-to-end Language Model Fine-tuning on Graphs”. Rui Xue, Xipeng Shen, Ruozhou Yu, Xiaorui Liu. ACM International Conference on Knowledge Discovery & Data Mining (KDD 2025).
- Savadikar, Chinmay and Song, Xi and Wu, Tianfu, WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models, ICML 2025.
- Saenko, A., Gajjar, P., Ganiyu, A., & Shah, V. K. (2026). Enhancing Confidence Estimation in Telco LLMs via Twin-Pass CoT-Ensembling. IEEE Vehicular Technology Conference (VTC), to appear. Preprint available at arXiv preprint arXiv:2604.13271.