Junyi Zhu

Orcid: 0000-0002-8980-5336

Affiliations:
  • KU Leuven, Belgium


According to our database1, Junyi Zhu authored at least 22 papers between 2019 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Decoding Text Spans for Efficient and Accurate Named-Entity Recognition.
CoRR, April, 2026

PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments.
CoRR, March, 2026

Diffusion Alignment Beyond KL: Variance Minimisation as Effective Policy Optimiser.
CoRR, February, 2026

Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

2025
Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification.
CoRR, September, 2025

Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations.
CoRR, May, 2025

Unlocking the Value of Decentralized Data: A Federated Dual Learning Approach for Model Aggregation.
CoRR, March, 2025

Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles.
Trans. Mach. Learn. Res., 2025

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024
Implicit Neural Representations for Robust Joint Sparse-View CT Reconstruction.
Trans. Mach. Learn. Res., 2024

Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs.
CoRR, 2024

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better.
CoRR, 2024

Rescaling Intermediate Features Makes Trained Consistency Models Perform Better.
Proceedings of the Second Tiny Papers Track at ICLR 2024, 2024

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023
Improving Differentially Private SGD via Randomly Sparsified Gradients.
Trans. Mach. Learn. Res., 2023

Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning.
Proceedings of the International Conference on Machine Learning, 2023

Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2021
Differentially Private SGD with Sparse Gradients.
CoRR, 2021

R-GAP: Recursive Gradient Attack on Privacy.
Proceedings of the 9th International Conference on Learning Representations, 2021

2019
Localization in Aerial Imagery with Grid Maps using LocGAN.
Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference, 2019

Learning Path Tracking for Real Car-like Mobile Robots From Simulation.
Proceedings of the 2019 European Conference on Mobile Robots, 2019


  Loading...