Fangcheng Fu

14 papers · 2020–2025 · 8 conferences · across top CS/AI conferences

Achievements

+9 more ↓

🌍 Conference Polyglot (8) 🏃 Academic Marathon (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (10)

🌈 Renaissance Researcher (7) 🗺️ Taxonomy Completionist (36) 🌉 Interdisciplinary Bridge 🤝 Dynamic Duo (11) 🏆 Grand Slam ❓ The Questioner ⚡ Prolific Year (7) 🗃️ Keyword Collector (68) 💎 Century Club (14)

Conferences

IJCAI (3) NIPS (3) AAAI (2) ICML (2) ACL (1) EMNLP (1) ICCV (1) ICLR (1)

Top co-authors

Bin CUI (11) Xupeng Miao (6) Jiawei Jiang (5) Shenhan Zhu (3) Wentao Zhang (3) Xiaonan Nie (3) Xiao Yan (2) Peichao Lai (2) YOUHE JIANG (2) Qinbo Zhang (2)

Research topics

Privacy (1)

Keywords

vertical federated learning (3) model parallelism (2) large language model (2) knowledge distillation (2) multi-task learning (1) sequence labeling (1) neural network compression (1) neural network optimization (1) contrastive learning (1) data augmentation (1) named entity recognition (1) distributed learning (1) privacy preservation (1) image editing (1) efficient inference (1) video generation (1) low-resource learning (1) deep learning (1) text-to-image generation (1) secure computation (1)

Papers

Model Rake: A Defense Against Stealing Attacks in Split Learning IJCAI 2025 HaCore: Efficient Coreset Construction with Locality Sensitive Hashing for Vertical Federated Learning AAAI 2025 Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning ACL 2025 Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations EMNLP 2025 Training-free and Adaptive Sparse Attention for Efficient Long Video Generation ICCV 2025 NetMoE: Accelerating MoE Training through Dynamic Sample Placement ICLR 2025 Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs ICML 2025 Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference AAAI 2024 LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing NIPS 2024 Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters NIPS 2024 X-former Elucidator: Reviving Efficient Attention for Long Context Language Modeling IJCAI 2024 OSDP: Optimal Sharded Data Parallel for Distributed Deep Learning IJCAI 2023 VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely? NIPS 2022 Don’t Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript ICML 2020