About me
I am a fifth-year PhD candidate at the department of Electrical and Computer Engineering, The Ohio State University (OSU), supervised by Prof. Yingbin Liang. I visited OSU as a summer research intern in 2018 and I obtained my B.E. degree from University of Science and Technology of China in 2019. My research involves LLM, generative AI, meta learning, bilevel optimization and adversarial attack in machine learning area.
Pre-prints:
X Chen, Z Wang, D Sow, J Yang, T Chen, Y Liang, M Zhou, Z Wang. “Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization”
J. Yang, J. Zhao, P. Wang, Z. Wang, Y. Liang. "Meta ControlNet: Enhancing Task Adaptation via Meta Learning" [Code]
J. Yang, T. Chen, X. Chen, Z. Wang, Y. Liang. "Rethinking PGD Attack: Is Sign Function Necessary?" [Code]
Publications
J. Yang, X. Chen, T. Chen, Z. Wang, Y. Liang. "M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation," ICLR 2023. [Code]
J. Yang*, T. Chen*, M. Zhu*, F. He, D. Tao, Y. Liang, Z. Wang. "Learning to Generalize Provably in Learning to Optimize," AISTATS 2023. [Code]
J. Yang, K. Ji, Y. Liang. "Provably Faster Algorithms for Bilevel Optimization," NeurIPS 2021, Spotlight. [Code]
K. Ji, J. Yang, Y. Liang. "Bilevel Optimization: Convergence Analysis and Enhanced Design," ICML 2021. [Code]
K. Ji, J. Yang, Y. Liang, “Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning,” JMLR 2021.
C. Chen, J. Yang, Y. Zhou. “Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study,” IEEE Bigdata 2020.
Y. Zhou, J. Yang, H. Zhang, Y. Liang, V. Tarokh, “SGD Converges to Global Minimum in Deep Learning via Star-convex Path,” ICLR 2019.
J. Yang, C. Wang, X. Wang, C. Shen, “A Machine Learning Approach to User Association in Enterprise Small Cell Networks,” IEEE/CIC ICCC 2018.
*denotes equal contribution
Experiences
05/2023 - 08/2023 Research Intern in Cruise LLC. Propose the route function for addressing domain shift issue caused by simulation data in LiDAR semantic segmentation problem.
05/2022 - 08/2022 PhD Machine Learning Engineer Intern in Uber NYC. Created customized PyTorch prediction model with personal designed SQL-based features, which have improved the Uber Rides ETA prediction accuracy 8%.
09/2018 – 06/2019 Attended SUGAR project, elected as the leader in USTC team, collaborating with Aalto university students to work for Xylem company.
07/2018 - 09/2018 Visited OSU as a summer research intern, worked in Prof. Yingbin Liang's lab.
08/2017 Attended the summer school in University of Twente (CuriousU)
Academical Services & Teaching
Served as Reviewer for ICML, NeurIPS, ICLR, CVPR, AISTATS, IEEE TIT, ISIT, etc.
Graduate Teaching Associate (GTA) in OSU ECE 2060, 2300 course
Honors & Reward
2019 The Ohio State University Fellowship Reward