Home Publications Services Teaching Students Code

Han-Jia Ye 叶翰嘉

Tenure-track Associate Professor

Learning And Mining from DatA (LAMDA) Group
School of Artificial Intelligence, Nanjing University
State Key Laboratory for Novel Software Technology

Email yehjxkxkxk@nju.edu.cn yehjxkxkxk@lamda.nju.edu.cn yhjyehanjiaxkxkxk@gmail.com
Open Positions Undergraduates are welcome for research internships; prospective Master’s and PhD students are encouraged to apply
Latest arXiv Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM RoutingarXiv:2609.37362 · 2026-09-29 · cs.AI
Talks Model Reuse Tutorial
Tabular Representation Learning Tutorial
Resources LAMDA-Tabular Organization
LAMDA-Model-Reuse Organization
Survey on Tabular Representation Learning
Survey on Model Reuse
Short Bio

Han-Jia Ye is a Tenure-track Associate Professor in the School of Artificial Intelligence at Nanjing University (NJU). His major research focuses on machine learning and its applications to data mining and computer vision, including model reuse, representation learning, tabular machine learning, meta-/continual learning, and multimodal large language models.

Han-Jia received his B.Sc. degree from Nanjing University of Posts and Telecommunications, China in June 2013. After that, he became an M.Sc. student in the LAMDA Group led by professor Zhi-Hua Zhou in Nanjing University. From Sept. 2015, Han-Jia started his Ph.D. degree in machine learning under the supervision of Prof. Yuan Jiang and Prof. De-Chuan Zhan. During 2017-2018, he visited Prof. Fei Sha's group in University of Southern California, LA. He received his PhD degree at May 2019.

01

Model Reuse

Capability representations and economical routing, towards reusable, collaborative, and evolving model systems.

Explore research →
02

Learning with Tabular Data

Learning across heterogeneous tables, from predictive and causal foundation models to executable data workflows.

Explore research →
03

Multimodal LLMs

Data-centric evaluation and efficient adaptation for multimodal large language models.

04

Continual Learning

Memory-efficient and pre-trained model based continual learning in dynamic environment.

05

Meta-learning

Few-shot learning, task understanding, and robust adaptation mechanisms.

Latest News Selected Publications [Google scholar] [DBLP]
Figure from TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery   Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye. TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery. In: Advances in Neural Information Processing Systems 39 (NeurIPS), 2026. [pdf][code][model]
Figure from When LLM Routers Overpay: Strong-Model Over-Selection under Loose Budgets   Guannan Lai, Long Chen, Han-Jia Ye. When LLM Routers Overpay: Strong-Model Over-Selection under Loose Budgets. In: Advances in Neural Information Processing Systems 39 (NeurIPS), 2026. [pdf][toolbox]
Figure from From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing   Guannan Lai, Haoran Hu, Long Chen, Zhenguo Li, Han-Jia Ye. From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing. In: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026. [pdf][code][data]
Figure from TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering   An-Yang Ji, Jun-Peng Jiang, De-Chuan Zhan, Han-Jia Ye. TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering. In: Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026. [pdf][code]
Figure from TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention   Si-Yang Liu, Han-Jia Ye. TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention. In: Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026. [pdf][code][model]
Figure from Multimodal Tabular Reasoning with Privileged Structured Information   Jun-Peng Jiang, Yu Xia, Hai-Long Sun, Shiyin Lu, Qing-Guo Chen, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye. Multimodal Tabular Reasoning with Privileged Structured Information. In: Advances in Neural Information Processing Systems 38 (NeurIPS), 2025. [pdf]
Figure from A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities   Han-Jia Ye, Si-Yang Liu, Wei-Lun Chao. A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities. In: Advances in Neural Information Processing Systems 38 (NeurIPS), 2025. [pdf]
Figure from Feature-aware Modulation for Learning from Temporal Tabular Data   Hao-Run Cai, Han-Jia Ye. Feature-aware Modulation for Learning from Temporal Tabular Data. In: Advances in Neural Information Processing Systems 38 (NeurIPS), 2025. [pdf][code]
Figure from Talent: A Tabular Analytics and Learning Toolbox   Si-Yang Liu, Hao-Run Cai, Qi-Le Zhou, Huai-Hong Yin, Tao Zhou, Jun-Peng Jiang, Han-Jia Ye. Talent: A Tabular Analytics and Learning Toolbox. Journal of Machine Learning Research, 26(226): 1-16, 2025. [pdf][code]
Figure from Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens   Ting-Ji Huang, Jia-Qi Yang, Chunxu Shen, Kai-Qi Liu, De-Chuan Zhan, Han-Jia Ye. Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens. In: Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025. [pdf]
Figure from Understanding the Limits of Deep Tabular Methods with Temporal Shift   Hao-Run Cai, Han-Jia Ye. Understanding the Limits of Deep Tabular Methods with Temporal Shift. In: Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025. [pdf][code]
Figure from TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems   Si-Yang Liu, Han-Jia Ye. TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems. In: Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025. [pdf]
Figure from Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later   Han-Jia Ye, Huai-Hong Yin, De-Chuan Zhan, Wei-Lun Chao. Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later. In: The 13th International Conference on Learning Representations (ICLR), 2025. [pdf][code]
Figure from ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs   Yi-Kai Zhang, Shiyin Lu, Qing-Guo Chen, De-Chuan Zhan, Han-Jia Ye. ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs. In: The 13th International Conference on Learning Representations (ICLR), 2025. [pdf]
Figure from Capability Instruction Tuning   Yi-Kai Zhang, De-Chuan Zhan, Han-Jia Ye. Capability Instruction Tuning. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI), 2025. [pdf][code]
Figure from Bridge the Modality and Capability Gaps in Vision-Language Model Selection   Chao Yi, Yu-Hang He, De-Chuan Zhan, Han-Jia Ye. Bridge the Modality and Capability Gaps in Vision-Language Model Selection. In: Advances in Neural Information Processing Systems 37 (NeurIPS), 2024. [pdf][code]
Figure from The Capacity and Robustness Trade-Off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting   Lu Han, Han-Jia Ye, De-Chuan Zhan. The Capacity and Robustness Trade-Off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting. IEEE Transactions on Knowledge and Data Engineering, 36(11): 7129-7142, 2024. [pdf][code]
Figure from Contextualizing Meta-Learning via Learning to Decompose   Han-Jia Ye, Da-Wei Zhou, Lanqing Hong, Zhenguo Li, Xiu-Shen Wei, De-Chuan Zhan. Contextualizing Meta-Learning via Learning to Decompose. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(1): 117-133, 2024. [pdf][code]
Figure from Few-Shot Learning with a Strong Teacher   Han-Jia Ye, Lu Ming, De-Chuan Zhan, Wei-Lun Chao. Few-Shot Learning with a Strong Teacher. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(3): 1425-1440, 2024. [pdf][code]
Figure from Model Spider: Learning to Rank Pre-Trained Models Efficiently   Yi-Kai Zhang, Ting-Ji Huang, Yao-Xiang Ding, De-Chuan Zhan, Han-Jia Ye. Model Spider: Learning to Rank Pre-Trained Models Efficiently. In: Advances in Neural Information Processing Systems 36 (NeurIPS), 2023. [pdf][code]
Figure from Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks   Han-Jia Ye, Lu Han, De-Chuan Zhan. Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3): 3721-3737, 2023. [pdf][code]
Figure from Generalized Knowledge Distillation via Relationship Matching   Han-Jia Ye, Su Lu, De-Chuan Zhan. Generalized Knowledge Distillation via Relationship Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2): 1817-1834, 2023. [pdf][code]
Figure from Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlaps   Lu Han, Han-Jia Ye, De-Chuan Zhan. Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlaps. In: The 11th International Conference on Learning Representations (ICLR), 2023. [pdf][code]
Figure from A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning   Da-Wei Zhou, Qi-Wei Wang, Han-Jia Ye, De-Chuan Zhan. A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning. In: The 11th International Conference on Learning Representations (ICLR), 2023. [pdf][code]
Figure from How to Train Your MAML to Excel in Few-Shot Classification   Han-Jia Ye, Le Gan, De-Chuan Zhan. How to Train Your MAML to Excel in Few-Shot Classification. In: The 10th International Conference on Learning Representations (ICLR), 2022. [pdf][code]
Figure from Heterogeneous Few-Shot Model Rectification with Semantic Mapping   Han-Jia Ye, De-Chuan Zhan, Yuan Jiang, Zhi-Hua Zhou. Heterogeneous Few-Shot Model Rectification with Semantic Mapping. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(11): 3878-3891, 2021. [pdf][code]
Figure from Multi-Instance Learning With Emerging Novel Class   Xiu-Shen Wei*, Han-Jia Ye*, Xin Mu, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou. Multi-Instance Learning With Emerging Novel Class. IEEE Transactions on Knowledge and Data Engineering, 33(5): 2109-2120, 2021. [pdf]
Figure from Procrustean Training for Imbalanced Deep Learning   Han-Jia Ye, De-Chuan Zhan, Wei-Lun Chao. Procrustean Training for Imbalanced Deep Learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021. [pdf]
Figure from Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning   Han-Jia Ye, Hong-You Chen, De-Chuan Zhan, Wei-Lun Chao. Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning. CoRR, abs/2001.01385, 2020. [pdf]
Figure from Learning Multiple Local Metrics: Global Consideration Helps   Han-Jia Ye, De-Chuan Zhan, Nan Li, Yuan Jiang. Learning Multiple Local Metrics: Global Consideration Helps. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(7): 1698-1712, 2020. [pdf]
Figure from Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach   Han-Jia Ye, Xiang-Rong Sheng, De-Chuan Zhan. Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach. Machine Learning, 109(3): 643-664, 2020. [pdf][code]
Figure from Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions   Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, Fei Sha. Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [pdf][code]
Figure from What Makes Objects Similar: A Unified Multi-Metric Learning Approach   Han-Jia Ye, De-Chuan Zhan, Yuan Jiang, Zhi-Hua Zhou. What Makes Objects Similar: A Unified Multi-Metric Learning Approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(5): 1257-1270, 2019. [pdf][code]
Figure from A Meta Understanding of Meta-Learning   Wei-Lun Chao*, Han-Jia Ye*, De-Chuan Zhan, Mark Campbell, Kilian Q. Weinberger. A Meta Understanding of Meta-Learning. In: The Adaptive and Multitask Learning (AMTL) 2019 Workshop, 2019. [pdf]
Figure from Fast generalization rates for distance metric learning   Han-Jia Ye, De-Chuan Zhan, Yuan Jiang. Fast generalization rates for distance metric learning. Machine Learning, 108(2): 267-295, 2019. [pdf]
Figure from Rectify Heterogeneous Models with Semantic Mapping   Han-Jia Ye, De-Chuan Zhan, Yuan Jiang, Zhi-Hua Zhou. Rectify Heterogeneous Models with Semantic Mapping. In: Proceedings of the 35th International Conference on Machine Learning (ICML), 2018. [pdf][code]
Figure from Learning Mahalanobis Distance Metric: Considering Instance Disturbance Helps   Han-Jia Ye, De-Chuan Zhan, Xue-Min Si, Yuan Jiang. Learning Mahalanobis Distance Metric: Considering Instance Disturbance Helps. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), 2018. [pdf][code]
Figure from What Makes Objects Similar: A Unified Multi-Metric Learning Approach   Han-Jia Ye, De-Chuan Zhan, Yuan Jiang, Zhi-Hua Zhou. What Makes Objects Similar: A Unified Multi-Metric Learning Approach. In: Advances in Neural Information Processing Systems 29 (NIPS), 2016. [pdf][code]
Figure from Instance Specific Metric Subspace Learning: A Bayesian Approach   Han-Jia Ye, De-Chuan Zhan, Yuan Jiang. Instance Specific Metric Subspace Learning: A Bayesian Approach. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI), 2016. [pdf]
Figure from Rank Consistency based Multi-View Learning: A Privacy-Preserving Approach   Han-Jia Ye, De-Chuan Zhan, Yuan Miao, Yuan Jiang, Zhi-Hua Zhou. Rank Consistency based Multi-View Learning: A Privacy-Preserving Approach. In: Proceedings of the 24th ACM International Conference on Information and Knowledge Management (CIKM), 2015. [pdf][code]
Services

Senior Area Chair for ICLR 2027 and IJCAI 2025.

Associate Editor for TPAMI, Action Editor for TMLR, and Neural Networks.

Area Chair for ICLR 2026, AAAI 2026, CVPR 2026, ICLR 2025, ICML 2025, CVPR 2025, IJCAI 2025, ICML 2024, NeurIPS 2024, CVPR 2024, SDM 2023, SDM 2022, ECML 2020.

Tutorial Co-Chair for SDM 2023

Doctoral Forum Co-Chair for SDM 2022

Reviewer for JMLR, TPAMI, AIJ, TKDE, TKDD, TNNLS, MLJ, etc.

Reviewer/PC Member for ICML/NeurIPS/ICLR/AAAI/IJCAI/CVPR/ICCV, etc.

Teaching Students
Name Master/PhD Period Destination
Jun-Peng Jiang PhD 2021- (Co-supervised with Prof. De-Chuan Zhan)
Yi-Kai Zhang PhD 2021- (Co-supervised with Prof. De-Chuan Zhan)
Qi-Wei Wang MasterAlumni 2021-2024 Tencent (WeChat)
Ting-Ji Huang MasterAlumni 2022-2025 Huawei Terminal
Lu Ren MasterAlumni 2022-2025 Kuaishou
Chao Yi MasterAlumni 2022-2025 Alibaba
Qi-Le Zhou MasterAlumni 2022-2025 ByteDance
Xu-Yang Chen MasterAlumni 2023-2026 ByteDance
Hai-Long Sun MasterAlumni 2023-2026 Ant Ling Team
Huai-Hong Yin MasterAlumni 2023-2026 Xiaohongshu
Tao Zhou MasterAlumni 2023-2026 Huawei Nanjing Research Institute
Yu-Hang He PhD 2024- -
Yu-Sheng Li Master 2024- -
Si-Yang Liu Master 2024- -
Yan Wang Master 2024- -
Xu-Xiang Zhong Master 2024- -
Hao-Run Cai PhD 2025- -
An-Yang Ji Master 2025- -
Guannan Lai Master 2025- -
Hao-Xuan Ma Master 2025- -
Guo Yu Master 2025- -
Ge-Lin Bian PhD 2026- -
Heng-Zhuang Li PhD 2026- -
Tian-Hao Ren PhD 2026- -
Jin-Hao Sheng PhD 2026- -
Cun-Da Wang PhD 2026- -
Zhen Xu PhD 2026- -
Zi-Rong Li PhD 2026- -
Shao-De Dong Master 2026- -
Zong-Da Li Master 2026- -
Di-Fei Song Master 2026- -
Code

Last Update@2026.10 by Han-Jia Ye.