Hong Huang 黄弘

Biography

I am a Ph.D. candidate supervised by Prof. Dapeng Oliver Wu at City University of Hong Kong. I obtained my M.Sc. degree from the University of Florida, advised by Prof. Dapeng Oliver Wu and Prof. Ruogu Fang. I obtained my B.E. degree from Shanghai Jiao Tong University.

Research Interests

My research focuses on Efficient & Reliable AI, with the overarching goal of AI Democratization, making powerful and reliable AI accessible to everyone.

• Efficient Large Models (Bar Menu): 🥂 Sherry ACL'26 (Oral) 🍸 Tequila ICLR'26 🥃 Aquavit SIGKDD'26 🍻 Quaff ACL'25
• Efficient Federated Learning (Fed Series): FedFit ICML'26 AquaFed IEEE TCC'26 FedRTS NeurIPS'25 FedMef CVPR'24 FedTiny ICDCS'23
• Efficient ML System (.cpp Series): Prima.cpp ICLR'26
• Reliable AI (Instrument Series): Violin Preprint

News

• 2026-05 Two works, FedFit and UCS-Bench, were accepted by ICML 2026.
• 2026-04 Sherry was accepted by ACL 2026 (Oral).
• 2026-03 AquaFed was accepted by IEEE TCC 2026.
• 2026-01 Two works, Tequila and Prima.cpp, were accepted by ICLR 2026.
• 2025-11 I was selected as a DAAD AINet Fellow (Postdoc-NeT-AI 11/2025).
• 2025-09 FedRTS was accepted by NeurIPS 2025.
• 2025-08 I received the Research Tuition Scholarship from CityU.
• 2025-05 Quaff was accepted by ACL 2025.

Selected Publications

(*Equal Contribution, †Corresponding Author)

• ACL 2026 (Oral) Hong Huang, Decheng Wu, Qiangqiang Hu, Guanghua Yu, Jinhai Yang, Jianchen Zhu, Xue Liu, and Dapeng Wu. “Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification.” [Paper] [Code]
• ICML 2026 Meng Bi, Hong Huang†, Jinlong Song, Charles Wang, Chengming Hu, Xi Chen, Ting Yu, Xue Liu. “FedFit: Federated Dynamic Pruning via Fisher Information Scoring.” [Paper]
• IEEE TCC 2026 Juntao Hu*, Hong Huang*, Kuan Liu, Huimin Lu, Bingyi Liu, Dapeng Wu. “AquaFed: Ascending Quantized Federated Learning on Heterogeneous Devices.” [Paper]
• ICLR 2026 Hong Huang, Decheng Wu, Rui Cen, Guanghua Yu, Zonghang Li, Kai Liu, Jianchen Zhu, Peng Chen, Xue Liu, Dapeng Wu. “Tequila: Trapping-free Ternary Quantization for Large Language Models.” [Paper] [Code]
• NeurIPS 2025 Hong Huang, Hai Yang, Yuan Chen, Jiaxun Ye, Dapeng Wu. “FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling.” [Paper] [Code]
• ACL 2025 Hong Huang, Dapeng Wu. “Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis.” [Paper] [Code]
• CVPR 2024 Hong Huang, Weiming Zhuang, Chen Chen, and Lingjuan Lyu. “FedMef: Towards Memory-efficient Federated Dynamic Pruning.” [Paper] [Code]
• ICDCS 2023 Hong Huang, Lan Zhang, Chaoyue Sun, Ruogu Fang, Xiaoyong Yuan, and Dapeng Wu. “Distributed Pruning Towards Tiny Neural Networks in Federated Learning.” [Paper] [Code]