| CARVIEW |
University of CambridgeI am a Postdoctoral Research Associate at the University of Cambridge, working with Prof. Robert Mullins. I received my Ph.D. in Computer Science from the University of Hong Kong (HKU), where I was affiliated with mmlab@HKU and advised by Prof. Ping Luo. During my Ph.D., I also collaborated with the UTDA Lab at The University of Texas at Austin, under the guidance of Prof. David Z. Pan (IEEE/ACM Fellow). Previously, I obtained my M.Eng. degree from the Software School at Tsinghua University, advised by Prof. Xiaojun Ye, and my B.Eng. degree from the Department of Microelectronics at Fudan University, advised by Prof. Xuan Zeng and Prof. Minge Jing. My research interests include AI for Electronic Design Automation (AI4EDA), AI for security, and related applications.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
The University of Hong KongPh.D. in Computer ScienceSep. 2021 - Nov. 2025 -
Tsinghua UniversityM.Eng. in Software EngineeringSep. 2017 - Jul. 2020 -
Fudan UniversityB.Eng. in Electronics EngineeringSep. 2013 - Jul. 2017
Experience
-
University of CambridgePostdoctoral Research AssociateDec. 2025 - Present
-
The University of Texas at AustinVisiting PhD StudentFeb. 2024 - Jul. 2024
Honors & Awards
-
NeurIPS Scholar Award2024
-
Hong Kong PhD Fellowship2021
-
HKU Presidential PhD Scholar2021
-
Outstanding Graduate of Software School, Tsinghua University2020
-
Outstanding Bachelor Thesis Award, Fudan University2017
-
Outstanding Graduate of Shanghai, China2017
-
National Scholarship, China2015
Selected Publications (view all )
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
Jin Wang*, Yao Lai*, Aoxue Li, Shifeng Zhang, Jiacheng Sun, Zhenguo Li, Ping Luo (* equal contribution)
Conference on Neural Information Processing Systems (NeurIPS) 2025 Spotlight
FUDOKI is a novel unified multimodal model that replaces traditional autoregressive architectures with discrete flow matching, enabling more flexible and effective visual understanding and image generation with performance comparable to state-of-the-art models.
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
Jin Wang*, Yao Lai*, Aoxue Li, Shifeng Zhang, Jiacheng Sun, Zhenguo Li, Ping Luo (* equal contribution)
Conference on Neural Information Processing Systems (NeurIPS) 2025 Spotlight
FUDOKI is a novel unified multimodal model that replaces traditional autoregressive architectures with discrete flow matching, enabling more flexible and effective visual understanding and image generation with performance comparable to state-of-the-art models.
AnalogCoder: Analog Circuit Design via Training-Free Code Generation
Yao Lai, Sungyoung Lee, Guojin Chen, Souradip Poddar, Mengkang Hu, David Z. Pan, Ping Luo
AAAI Conference on Artificial Intelligence (AAAI) 2025 Oral
AnalogCoder is a training-free LLM agent for analog circuit design, using feedback-driven prompts and a circuit library to achieve high success rates, outperforming GPT-4o by designing various circuits.
AnalogCoder: Analog Circuit Design via Training-Free Code Generation
Yao Lai, Sungyoung Lee, Guojin Chen, Souradip Poddar, Mengkang Hu, David Z. Pan, Ping Luo
AAAI Conference on Artificial Intelligence (AAAI) 2025 Oral
AnalogCoder is a training-free LLM agent for analog circuit design, using feedback-driven prompts and a circuit library to achieve high success rates, outperforming GPT-4o by designing various circuits.
Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs
Yao Lai, Jinxin Liu, David Z. Pan, Ping Luo
Conference on Neural Information Processing Systems (NeurIPS) 2024 Spotlight
This work uses reinforcement learning to optimize adder and multiplier designs as tree generation tasks, achieving up to 49% faster speed and 45% smaller size, with scalability to 7nm technology.
Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs
Yao Lai, Jinxin Liu, David Z. Pan, Ping Luo
Conference on Neural Information Processing Systems (NeurIPS) 2024 Spotlight
This work uses reinforcement learning to optimize adder and multiplier designs as tree generation tasks, achieving up to 49% faster speed and 45% smaller size, with scalability to 7nm technology.
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer
Yao Lai, Jinxin Liu, Zhentao Tang, Bin Wang, Jianye Hao, Ping Luo
International Conference on Machine Learning (ICML) 2023
ChiPFormer is an offline RL-based method that achieves 10x faster chip placement with superior quality and transferability to unseen circuits.
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer
Yao Lai, Jinxin Liu, Zhentao Tang, Bin Wang, Jianye Hao, Ping Luo
International Conference on Machine Learning (ICML) 2023
ChiPFormer is an offline RL-based method that achieves 10x faster chip placement with superior quality and transferability to unseen circuits.
MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning
Yao Lai, Yao Mu, Ping Luo
Conference on Neural Information Processing Systems (NeurIPS) 2022 Spotlight
MaskPlace is a method that leverages pixel-level visual representation for chip placement, achieving superior performance with simpler rewards, 60%-90% wirelength reduction, and zero overlaps.
MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning
Yao Lai, Yao Mu, Ping Luo
Conference on Neural Information Processing Systems (NeurIPS) 2022 Spotlight
MaskPlace is a method that leverages pixel-level visual representation for chip placement, achieving superior performance with simpler rewards, 60%-90% wirelength reduction, and zero overlaps.