PPaperPicks

Qiang Yang

Hong Kong University of Science and Technology, Department of Computer Science, Kowloon, Hong Kong

21 papers at tracked venues · 13 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. FedGRPO: Privately Optimizing Foundation Models with Group-Relative Rewards from Domain Clients
  2. FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
  3. Federated Vision-Language-Recommendation with Personalized Fusion
  4. LoRA-E2: Effective and Efficient Low-rank Adaptation
  5. Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
  6. FedCoT: Federated Chain-of-Thought Distillation for Large Language Models
  7. Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor
  8. HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmark
  9. Model-based Large Language Model Customization as Service
  10. PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
  11. PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation
  12. A Survey on Cross-Domain Sequential Recommendation
  13. Complementary Knowledge Distillation for Robust and Privacy-Preserving Model Serving in Vertical Federated Learning
  14. Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
  15. Label Privacy Source Coding in Vertical Federated Learning
  16. Model Trip: Enhancing Privacy and Fairness in Model Fusion Across Multi-Federations for Trustworthy Global Healthcare
  17. Secure Dataset Condensation for Privacy-Preserving and Efficient Vertical Federated Learning
  18. Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
  19. The 13th International Workshop on Urban Computing
  20. The Good, The Bad, and Why: Unveiling Emotions in Generative AI
  21. Unlearning during Learning: An Efficient Federated Machine Unlearning Method