Fangcheng Fu

Venues

Frequent coauthors

Papers

1. Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
   ICML 2025 ·

   Youhe Jiang

   DBLP profile ↗ORCID search ↗
2. Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning
   ACL 2025 ·

   Peichao Lai

   DBLP profile ↗ORCID search ↗
3. HaCore: Efficient Coreset Construction with Locality Sensitive Hashing for Vertical Federated Learning
   AAAI 2025 ·

   Qinbo Zhang

   DBLP profile ↗ORCID search ↗
4. Hounding Data Diversity: Towards Participant Selection in Vertical Federated Learning
   ICDE 2025 ·

   Xiaokai Zhou

   DBLP profile ↗ORCID search ↗
5. Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment
   SIGMOD 2025 ·

   Haoyang Li

   DBLP profile ↗ORCID search ↗
6. Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations
   EMNLP 2025 ·

   Peichao Lai

   DBLP profile ↗ORCID search ↗
7. LobRA: Multi-tenant Fine-tuning over Heterogeneous Data
   VLDB 2025 ·

   Sheng Lin

   DBLP profile ↗ORCID search ↗
8. MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training
   SIGMOD 2025 ·

   Pinxue Zhao

   DBLP profile ↗ORCID search ↗
9. Malleus: Straggler-Resilient Hybrid Parallel Training of Large-scale Models via Malleable Data and Model Parallelization
   SIGMOD 2025 ·

   Haoyang Li

   DBLP profile ↗ORCID search ↗
10. Model Rake: A Defense Against Stealing Attacks in Split Learning
    IJCAI 2025 ·

    Qinbo Zhang

    DBLP profile ↗ORCID search ↗
11. NetMoE: Accelerating MoE Training through Dynamic Sample Placement
    ICLR 2025 ·

    Xinyi Liu

    DBLP profile ↗ORCID search ↗
12. PQCache: Product Quantization-based KVCache for Long Context LLM Inference
    SIGMOD 2025 ·

    Hailin Zhang

    DBLP profile ↗ORCID search ↗
13. PS-MI: Accurate, Efficient, and Private Data Valuation in Vertical Federated Learning
    VLDB 2025 ·

    Xiaokai Zhou

    DBLP profile ↗ORCID search ↗
14. ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments
    MLSys 2025 ·

    Youhe Jiang

    DBLP profile ↗ORCID search ↗
15. Towards Scalable and Efficient Graph Structure Learning
    ICDE 2025 ·

    Siqi Shen

    DBLP profile ↗ORCID search ↗
16. Training-Free and Adaptive Sparse Attention for Efficient Long Video Generation
    ICCV 2025 ·

    Yifei Xia

    DBLP profile ↗ORCID search ↗
17. Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference
    AAAI 2024 ·

    Zihao Yu

    DBLP profile ↗ORCID search ↗
18. Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
    NeurIPS 2024 ·

    Yifei Xia

    DBLP profile ↗ORCID search ↗
19. Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning
    ICDE 2024 ·

    Yuxiang Wang

    DBLP profile ↗ORCID search ↗
20. LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
    NeurIPS 2024 ·

    Xiaonan Nie

    DBLP profile ↗ORCID search ↗
21. X-former Elucidator: Reviving Efficient Attention for Long Context Language Modeling
    IJCAI 2024 ·

    Xupeng Miao

    DBLP profile ↗ORCID search ↗