Publications

Deep Neural Networks Acceleration

1. HARL: Hierarchical Adaptive Reinforcement Learning Based Auto Scheduler for Neural Networks.
   Zining Zhang, Bingsheng He, and Zhenjie Zhang.
   ICPP 2022: 51th International Conference on Parallel Processing
2. NIOT: A Novel Inference Optimization of Transformers on Modern CPUs.
   Zining Zhang, Yao Chen, Bingsheng He, and Zhenjie Zhang.
   TPDS 2023: IEEE Transactions on Parallel and Distributed Systems
3. Practical Edge Kernels for Integer-Only Vision Transformers Under Post-training Quantization.
   Zining Zhang, Bingsheng He, and Zhenjie Zhang.
   MLSys 2023: Sixth Conference on Machine Learning and Systems
4. LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation.
   Chen Han, Zicong Jiang, Zining Zhang, Bingsheng He, Luo Pingyi, Mian Lu, Yuqiang Chen.
   ICLR 2025 Workshop on Sparsity in LLMs (SLLM)
5. Efficient KV Cache Spillover Management on Memory-Constrained GPU for LLM Inference.
   Jiang Jiazhi, Chen Yao, Zhang Zining, He Bingsheng, etc.
   IEEE Transactions on Parallel and Distributed Systems (TPDS 2025)

Speech Processing

1. GAZEV: GAN-Based Zero-Shot Voice Conversion over Non-parallel Speech Corpus.
   Zining Zhang, Bingsheng He, and Zhenjie Zhang.
   INTERSPEECH 2020: 791-795
2. X-TaSNet: Robust and Accurate Time-Domain Speaker Extraction Network.
   Zining Zhang, Bingsheng He, and Zhenjie Zhang.
   INTERSPEECH 2020: 3959-3963
3. TransMask: A Compact and Fast Speech Separation Model Based on Transformer.
   Zining Zhang, Bingsheng He, and Zhenjie Zhang.
   ICASSP 2021: IEEE International Conference on Acoustics, Speech and Signal Processing

Database and Storage

1. PA-Tree: Polled-Mode Asynchronous B+ Tree for NVMe.
   Wang Li, Zining Zhang, Bingsheng He, and Zhenjie Zhang.
   ICDE 2020: IEEE 36th International Conference on Data Engineering
2. Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models.
   Wenqi Pei, Xu Hailing, Henry Zhao, Chen Han, Zining Zhang, Shizheng Hou, Luo Pingyi, Bingsheng He.
   ICLR 2025 The 3rd DL4C Workshop

Awards & Grants

• Research Achievement Award, 2023, National University of Singapore School of Computing
• Technology Acceleration Programme Grant, 2021, National University of Singapore

Patents

1. Zining Zhang, Xiaoyan Wang, Zhenjie Zhang. "A training method, a readable storage medium and a voice cloning method for a voice cloning model"
2. Zining Zhang, Xiaoyan Wang, Zhenjie Zhang. "A parallel speech synthesis method" (under application process)
3. Zining Zhang, Bingsheng He. "High Quality Voice Conversion System for Low-resource Languages"