Fingerprint
Dive into the research topics where Kaiyi Ji is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
Efficiently Escaping Saddle Points in Bilevel Optimization
Huang, M., Chen, X., Ji, K., Ma, S. & Lai, L., 2025, In: Journal of Machine Learning Research. 26Research output: Contribution to journal › Article › peer-review
2 Scopus citations -
First-Order Federated Bilevel Learning
Yang, Y., Xiao, P., Ma, S. & Ji, K., Apr 11 2025, In: Proceedings of the AAAI Conference on Artificial Intelligence. 39, 21, p. 22029-22037 9 p.Research output: Contribution to journal › Conference article › peer-review
Open Access2 Scopus citations -
Imperative learning: A self-supervised neuro-symbolic learning framework for robot autonomy
Wang, C., Ji, K., Geng, J., Ren, Z., Fu, T., Yang, F., Guo, Y., He, H., Chen, X., Zhan, Z., Du, Q., Su, S., Li, B., Qiu, Y., Du, Y., Li, Q., Yang, Y., Lin, X. & Zhao, Z., 2025, (Accepted/In press) In: International Journal of Robotics Research. 02783649251353181.Research output: Contribution to journal › Article › peer-review
Open Access6 Scopus citations -
Meta-learning with Heterogeneous Tasks
Si, Z., Hu, S., Ji, K. & Lyu, S., 2025, Generalizing from Limited Resources in the Open World - 3rd International Workshop, GLOW 2025, Held in Conjunction with IJCAI 2025, Proceedings. Ma, Y., Guo, J., Liu, X., Zhao, X., Gong, R., Liu, N. & Ning, X. (eds.). Springer Science and Business Media Deutschland GmbH, p. 74-94 21 p. (Communications in Computer and Information Science; vol. 2640 CCIS).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
-
MGDA CONVERGES UNDER GENERALIZED SMOOTHNESS, PROVABLY
Zhang, Q., Xiao, P., Zou, S. & Ji, K., 2025, 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, p. 92004-92035 32 p. (13th International Conference on Learning Representations, ICLR 2025).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review