Zihao Zeng

22 papers A* 3Journal 13Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
DP-FedPUAC: Federated learning with differential privacy via adaptive gradient clipping and local iteration optimization.
Inf. Sci.
Jiangyong Yuan, Yong Chen, Zheyi Wang, Chenxiao Wang, Xiaoyue Hu, Zihao Zeng
2026 — conf
SEMIROUTER: Sparse-Data Enhanced Routing for Adaptive Multi-LLM System.
EACL (Volume 1: Long Papers)
Zijie Wang, Xinyu Yan, Che Wang, Zihao Zeng, Lei Xiao, Wei Yang Bryan Lim
2025 J jnl
AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs.
CoRR
Zihao Zeng, Chubo Liu, Xin He, Juan Hu, Yong Jiang, Fei Huang, Kenli Li, Wei Yang Bryan Lim
2025 J jnl
Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition.
CoRR
Zihao Zeng, Xuyao Huang, Boxiu Li, Hao Zhang, Zhijie Deng
2025 J jnl
Generating invisible adversarial watermarks based on block-matching embedding algorithm.
Digit. Signal Process.
Chenxiao Wang, Zihao Zeng, Xiaoyue Hu, Yong Chen
2025 A* conf
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection.
ICLR
Bokai Lin, Zihao Zeng, Zipeng Xiao, Siqi Kou, Tianqi Hou, Xiaofeng Gao, Hao Zhang, Zhijie Deng
2025 J jnl
Probability analysis of shallow landslides in varying vegetation zones with random soil grain-size distribution.
Environ. Model. Softw.
Hu Jiang, Qiang Zou, Yong Li, Yao Jiang, Junfang Cui, Bin Zhou, Wentao Zhou, Siyu Chen, Zihao Zeng
2025 J jnl
RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability.
CoRR
Yichi Zhang, Zihao Zeng, Dongbai Li, Yao Huang, Zhijie Deng, Yinpeng Dong
2025 — conf
SIFT: Grounding LLM Reasoning in Contexts via Stickers.
EMNLP (Findings)
Zihao Zeng, Xuyao Huang, Boxiu Li, Zhijie Deng
2025 J jnl
SIFT: Grounding LLM Reasoning in Contexts via Stickers.
CoRR
Zihao Zeng, Xuyao Huang, Boxiu Li, Zhijie Deng
2025 J jnl
Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions.
CoRR
Siqi Kou, Qingyuan Tian, Hanwen Xu, Zihao Zeng, Zhijie Deng
2024 — conf
AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models.
EMNLP (Findings)
Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng
2024 J jnl
AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models.
CoRR
Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng
2024 — conf
An End-to-End Multi-modal-based Framework for Visual Identity Inspection System.
BDIOT
Jing Wang, Zihao Zeng, Haifeng Jiang, Zhijie Jin, Yang Mo, Yexing Zhang
2024 J jnl
ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference.
CoRR
Xin He, Shunkang Zhang, Yuxin Wang, Haiyan Yin, Zihao Zeng, Shaohuai Shi, Zhenheng Tang, Xiaowen Chu, Ivor W. Tsang, Yew-Soon Ong
2024 J jnl
In-context KV-Cache Eviction for LLMs via Attention-Gate.
CoRR
Zihao Zeng, Bokai Lin, Tianqi Hou, Hao Zhang, Zhijie Deng
2024 J jnl
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection.
CoRR
Bokai Lin, Zihao Zeng, Zipeng Xiao, Siqi Kou, Tianqi Hou, Xiaofeng Gao, Hao Zhang, Zhijie Deng
2022 J jnl
AccTFM: An Effective Intra-Layer Model Parallelization Strategy for Training Large-Scale Transformer-Based Models.
IEEE Trans. Parallel Distributed Syst.
Zihao Zeng, Chubo Liu, Zhuo Tang, Kenli Li, Keqin Li
2021 — conf
Balancing Performance and Effort in Deep Learning via the Fusion of Real and Synthetic Cultural Heritage Photogrammetry Training Sets.
ICAART (1)
Eugene Ch'ng, Pinyuan Feng, Hongtao Yao, Zihao Zeng, Danzhao Cheng, Shengdan Cai
2021 A* conf
Training Acceleration for Deep Neural Networks: A Hybrid Parallelization Strategy.
DAC
Zihao Zeng, Chubo Liu, Zhuo Tang, Wanli Chang, Kenli Li
2020 A* conf
CoExe: An Efficient Co-execution Architecture for Real-Time Neural Network Services.
DAC
Chubo Liu, Kenli Li, Mingcong Song, Jiechen Zhao, Keqin Li, Tao Li, Zihao Zeng
2019 — conf
K-Means Parallel Acceleration for Sparse Data Dimensions on Flink.
HPCC/SmartCity/DSS
Zihao Zeng, Kenli Li, Mingxing Duan, Chubo Liu, Xiangke Liao