---

Brief Biography

I am currently a Senior Research Scientist at CENTRE FOR FRONTIER AI RESEARCH (CFAR) in Agency for Science, Technology and Research (A*STAR), working with Prof. Ivor W. Tsang, Prof. Atsushi Nitanda, and Prof. Yew-Soon Ong. I obtained my Ph.D. degree from the Australian Artificial Intelligence Institute(AAII) in University of Technology Sydney(UTS), supervised by Prof. Ivor W. Tsang. I received my B.Eng degree and M.Eng degree in Computer Science and Technology from South China University of Technology.

---

Openning

I am looking for self-motivated students to work with me on cutting-edge research projects. I accept PhD students, research interns, and CSC visiting students supported by my funding/grants or scholarships (e.g., A*STAR SINGA Scholarship , A*STAR SIPGA Scholarship and ARAP ).

---

News

• Three papers are accepted to NeurIPS 2026.

• One paper is accepted to EMNLP 2026.

• I was invited to give a talk at the Workshop on Data-Driven Scientific Computing at the National University of Singapore (NUS). The title of my talk is Efficient Sampling, Optimization, and Targeted Diffusion Generation for Physical AI.

• Serving as Area Chair for ICLR 2027.

• Our NeCLO Optimizer for Electromagnetics is accepted for Oral Presentation in the AI4X Conference 2026.

• One paper is accepted to SIGKDD 2026.

• Happy to share our new preprints for guided generation, Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation, which offers a new theoretically grounded principle for training-free guided generation, and Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field, which provides query-efficient and reusable Non-Parametric Guidance without requiring repeated queries.

• Serving as Area Chair for NeurIPS 2026.

• One paper is accepted to ICML 2026.

• Two papers are accepted to ICLR 2026.

• One paper is accepted to NeurIPS 2025.

• Serving as Workflow Chair for AAAI26-Trustworthy Agentic AI Workshop.

• Serving as Area Chair for ICLR 2026.

• One paper is accepted to TMLR.

• One paper is accepted to ICML 2025.

• Two papers are accepted to ICLR 2025.

---

My Research

My research interests lie primarily in the area of statistical machine learning and optimization. I am currently focusing on the following topics:

• Black-box Optimization, Reinforcement Learning (RL) and Agentic AI

• Quasi-Monte Carlo (QMC), Kernel Methods and Physical Solvers

---

Selected Recent Publications and Preprints

^* denotes equal contribution. ^# denotes corresponding author

• Black-box Optimization, RL and Agentic AI:

• Atsushi Nitanda, Dake Bu, Yueming Lyu, Tanya Veeravalli. Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation. Accepted in Conference on Neural Information Processing Systems (NeurIPS), 2026

• Kim Yong Tan , Yueming Lyu^#, Ivor Tsang, Yew-Soon Ong. Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field. Accepted in Conference on Neural Information Processing Systems (NeurIPS), 2026

• Jie-Jing Shao, Haiyan Yin, Yueming Lyu, Xingrui Yu, Lan-Zhe Guo, Ivor Tsang, James Kwok, Yu-Feng Li. Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks. Accepted In International Conference on Machine Learning (ICML), 2026

• Melvin Wong, Yueming Lyu, Thiago Rios, Stefan Menzel, Yew-Soon Ong LLM-to-Phy3D: Physically Conform Online 3D Object Generation with LLMs. Accepted in WCCI 2026

• Keyi Xiang, Zeyu Feng, Zhuoyi Lin, Yueming Lyu, Shi Boyuan, Yew-Soon Ong, Ivor Tsang, Haiyan Yin FlowSearcher: Synthesizing Memory-Guided Agentic Workflows for Web Information Seeking In International Conference on Learning Representations (ICLR), 2026

• Shenggui Li, Runyu Lu, qiaoling chen, Haiyan Yin, Yueming Lyu, Yonggang Wen, Ivor Tsang, Tianwei Zhang DSA: Efficient Inference For Video Generation Models via Distributed Sparse Attention In International Conference on Learning Representations (ICLR), 2026

• Chengqi Zheng, Jianda Chen, Yueming Lyu, Wen Zheng Terence Ng, Haopeng Zhang, Yew-Soon Ong, Ivor Tsang, Haiyan Yin. MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming. Preprint

• Yueming Lyu, Atsushi Nitanda, Ivor W. Tsang. Nonparametric Distributional Black-box Optimization via Diffusion Process. In ICLR 2025 DeLTa Workshop , 2025

• Yueming Lyu, Kim Yong Tan, Yew-Soon Ong, Ivor W. Tsang. Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation. Preprint

• Yueming Lyu, Xiaowei Zhou, Xingrui Yu, Ivor W. Tsang. Graph Potential Field Neural Network for Massive Agents Group-wise Path Planning. Transactions on Machine Learning Research (TMLR), 2025

• Zhenglin Wan, Xingrui Yu, David Mark Bossens, Yueming Lyu, Qing Guo, Flint Xiaofeng Fan, Yew-Soon Ong, Ivor Tsang. Diversifying Robot Locomotion Behaviors with Extrinsic Behavioral Curiosity. In International Conference on Machine Learning (ICML), 2025

• Kim Yong Tan, Yueming Lyu^#, Ivor W. Tsang, Yew-Soon Ong. Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation. In International Conference on Learning Representations (ICLR), 2025

• Feiyang Ye^*, Yueming Lyu^* , Xuehao Wang, Masashi Sugiyama, Yu Zhang, Ivor W. Tsang. Sharpness-Aware Black-Box Optimization. In International Conference on Learning Representations (ICLR), 2025

• Xingrui Yu, Zhenglin Wan, David Mark Bossens, Yueming Lyu, Qing Guo, Ivor Tsang. Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration. In International Conference on Autonomous Agents and Multiagent Systems(AAMAS) , 2025

• Feiyang Ye^*, Yueming Lyu^* , Xuehao Wang, Yu Zhang, Ivor W. Tsang. Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning. In International Conference on Learning Representations (ICLR), 2024

• Yueming Lyu. Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization. In Conference on Neural Information Processing Systems (NeurIPS), 2023

• Jing Li, Yuangang Pan, Yueming Lyu, Yinghua Yao, Yulei Sui, Ivor W. Tsang Earning Extra Performance from Restrictive Feedbacks. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2023

• Yueming Lyu and Ivor W. Tsang. Black-box Optimizer with Implicit Natural Gradient. In European Conference on Machine Learning. (ECML), 2021

• Yueming Lyu, Yuan Yuan and Ivor W. Tsang. Efficient Batch Black-box Optimization with Deterministic Regret Bounds. Preprint.

• Xingrui Yu, Yueming Lyu and Ivor W. Tsang. Intrinsic Reward Driven Imitation Learning via Generative Model. In International Conference on Machine Learning (ICML), 2020

• QMC and Kernel Methods:

• Pengyuan Zhu, Ivor W. Tsang, Yueming Lyu^#. IKNO: Infinite-order Kernel Neural Operators. ICML 2026 Workshop on AI for Physics, 2026.

• Yueming Lyu and Ivor W. Tsang. Neural Optimization Kernel: Towards Robust Deep Learning. Preprint.

• Yueming Lyu, Yuan Yuan and Ivor W. Tsang. Subgroup-based Rank-1 Lattice Quasi-Monte Carlo. Conference on Neural Information Processing Systems (NeurIPS), 2020

• Yueming Lyu. Spherical structured feature maps for kernel approximation. In International Conference on Machine Learning (ICML), 2017

• Robust Learning and Weakly-supervised Learning:

• Feng Hong, Yueming Lyu, Jiangchao Yao, Ya Zhang, Ivor Tsang, Yanfeng Wang. Diversified Batch Selection for Training Acceleration. In International Conference on Machine Learning (ICML), 2024

• Feng Hong, Jiangchao Yao, Yueming Lyu, Zhihan Zhou, Ivor Tsang, Ya Zhang, Yanfeng Wang. On Harmonizing Implicit Subpopulations. In International Conference on Learning Representations (ICLR), 2024

• Yueming Lyu and Ivor W. Tsang. Curriculum Loss: Robust Learning and Generalization against Label Corruption. In International Conference on Learning Representations (ICLR), 2020

• Yuan Yuan, Yueming Lyu, Xi Shen, Ivor W. Tsang, Dit-Yan Yeung. Marginalized average attentional network for weakly-supervised learning. In International Conference on Learning Representations (ICLR), 2019

---

Academic Service

• Area Chair:

• NeurIPS, ICLR

• Conference Reviewer/PC Member:

• ICML, AISTATS, AAAI, IJCAI, ACML

• Journal Reviewer:

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

• Transactions on Machine Learning Research (TMLR)

• International Journal of Computer Vision (IJCV)

• Journal of Artificial Intelligence Research (JAIR)

• IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

• Machine Learning