Junyi Zhu

According to our database, Junyi Zhu authored at least 16 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles.

Zifu Wang, Junyi Zhu, Bo Tang, Zhiyu Li, Feiyu Xiong, Jiaqian Yu, Matthew B. Blaschko

CoRR, May, 2025

Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations.

Bo Tang, Junyi Zhu, Chenyang Xi, Yunhang Ge, Jiahao Wu, Yuchen Feng, Yijun Niu, Wenqiang Wei, Yu Yu, Chunyu Li, Zehao Lin, Hao Wu, Ning Liao, Yebin Yang, Jiajia Wang, Zhiyu Li, Feiyu Xiong, Jingrun Chen

CoRR, May, 2025

Unlocking the Value of Decentralized Data: A Federated Dual Learning Approach for Model Aggregation.

Junyi Zhu, Ruicong Yao, Taha Ceritli, Savas Özkan, Matthew B. Blaschko, Eunchung Noh, Jeongwon Min, Cho Jung Min, Mete Ozay

CoRR, March, 2025

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better.

Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Implicit Neural Representations for Robust Joint Sparse-View CT Reconstruction.

Jiayang Shi, Junyi Zhu, Daniël Maria Pelt, Kees Joost Batenburg, Matthew B. Blaschko

Trans. Mach. Learn. Res., 2024

Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs.

Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang

CoRR, 2024

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better.

Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang

CoRR, 2024

Rescaling Intermediate Features Makes Trained Consistency Models Perform Better.

Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko

Proceedings of the Second Tiny Papers Track at ICLR 2024, 2024

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models.

Junyi Zhu, Shuochen Liu, Yu Yu, Bo Tang, Yibo Yan, Zhiyu Li, Feiyu Xiong, Tong Xu, Matthew B. Blaschko

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023

Improving Differentially Private SGD via Randomly Sparsified Gradients.

Junyi Zhu, Matthew B. Blaschko

Trans. Mach. Learn. Res., 2023

Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning.

Junyi Zhu, Ruicong Yao, Matthew B. Blaschko

Proceedings of the International Conference on Machine Learning, 2023

Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization.

Junyi Zhu, Xingchen Ma, Matthew B. Blaschko

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2021

Differentially Private SGD with Sparse Gradients.

Junyi Zhu, Matthew B. Blaschko

CoRR, 2021

R-GAP: Recursive Gradient Attack on Privacy.

Junyi Zhu, Matthew B. Blaschko

Proceedings of the 9th International Conference on Learning Representations, 2021

2019

Localization in Aerial Imagery with Grid Maps using LocGAN.

Haohao Hu, Junyi Zhu, Sascha Wirges, Martin Lauer

Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference, 2019

Learning Path Tracking for Real Car-like Mobile Robots From Simulation.

Danial Kamran, Junyi Zhu, Martin Lauer

Proceedings of the 2019 European Conference on Mobile Robots, 2019