Scholar

Junyi Zhu

Google Scholar ID: 3LeC4cMAAAAJ

Samsung Research UK (SRUK)

Generative ModelsEfficient AlgorithmsDistributed LearningPrivacy-Preserving Learning

Citations & Impact

All-time

Citations

345

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

1 items

2026

Cited

Resume (English only)

Academic Achievements

Paper 'Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification' accepted at NeurIPS 2025
Paper 'Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models' accepted at WACV 2026 (Round 1 acceptance rate: 6.3%)
Paper 'Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better' accepted at ICLR 2025 (co-first author)
Paper 'FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models' published in EMNLP Findings 2024 (co-first author)
Paper 'Confidence-aware Personalized Federated Learning via Variational Expectation Maximization' published at CVPR 2023 (co-first author)
Paper 'Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning' published at ICML 2023
Paper 'Implicit Neural Representations for Robust Joint Sparse-View CT Reconstruction' published in TMLR 2024 (co-first author)
Serving as Area Chair for CVPR 2026

Background

Currently a Senior Researcher at Samsung Electronics R&D Institute UK (SRUK)
Focuses on advanced AI algorithm research
Passionate and curious about AI technologies, aiming to apply AI to industry and daily life
Research interests include image generation models, large language models, distributed learning, and privacy-preserving machine learning
Looks forward to the realization of Artificial General Intelligence (AGI)

Co-authors

26 total