Zihao Zeng

According to our database, Zihao Zeng authored at least 18 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions.

Siqi Kou, Qingyuan Tian, Hanwen Xu, Zihao Zeng, Zhijie Deng

CoRR, May, 2025

Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition.

Zihao Zeng, Xuyao Huang, Boxiu Li, Hao Zhang, Zhijie Deng

CoRR, May, 2025

RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability.

Yichi Zhang, Zihao Zeng, Dongbai Li, Yao Huang, Zhijie Deng, Yinpeng Dong

CoRR, April, 2025

AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs.

Zihao Zeng, Chubo Liu, Xin He, Juan Hu, Yong Jiang, Fei Huang, Kenli Li, Wei Yang Bryan Lim

CoRR, March, 2025

SIFT: Grounding LLM Reasoning in Contexts via Stickers.

Zihao Zeng, Xuyao Huang, Boxiu Li, Zhijie Deng

CoRR, February, 2025

Probability analysis of shallow landslides in varying vegetation zones with random soil grain-size distribution.

Hu Jiang, Qiang Zou, Yong Li, Yao Jiang, Junfang Cui, Bin Zhou, Wentao Zhou, Siyu Chen, Zihao Zeng

Environ. Model. Softw., 2025

Generating invisible adversarial watermarks based on block-matching embedding algorithm.

Chenxiao Wang, Zihao Zeng, Xiaoyue Hu, Yong Chen

Digit. Signal Process., 2025

MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection.

Bokai Lin, Zihao Zeng, Zipeng Xiao, Siqi Kou, TianQi Hou, Xiaofeng Gao, Hao Zhang, Zhijie Deng

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference.

Xin He, Shunkang Zhang, Yuxin Wang, Haiyan Yin, Zihao Zeng, Shaohuai Shi, Zhenheng Tang, Xiaowen Chu, Ivor W. Tsang, Yew-Soon Ong

CoRR, 2024

In-context KV-Cache Eviction for LLMs via Attention-Gate.

Zihao Zeng, Bokai Lin, Tianqi Hou, Hao Zhang, Zhijie Deng

CoRR, 2024

AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models.

Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng

CoRR, 2024

AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models.

Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

An End-to-End Multi-modal-based Framework for Visual Identity Inspection System.

Jing Wang, Zihao Zeng, Haifeng Jiang, Zhijie Jin, Yang Mo, Yexing Zhang

Proceedings of the 2024 8th International Conference on Big Data and Internet of Things, 2024

2022

AccTFM: An Effective Intra-Layer Model Parallelization Strategy for Training Large-Scale Transformer-Based Models.

Zihao Zeng, Chubo Liu, Zhuo Tang, Kenli Li, Keqin Li

IEEE Trans. Parallel Distributed Syst., 2022

2021

Balancing Performance and Effort in Deep Learning via the Fusion of Real and Synthetic Cultural Heritage Photogrammetry Training Sets.

Eugene Ch'ng, Pinyuan Feng, Hongtao Yao, Zihao Zeng, Danzhao Cheng, Shengdan Cai

Proceedings of the 13th International Conference on Agents and Artificial Intelligence, 2021

Training Acceleration for Deep Neural Networks: A Hybrid Parallelization Strategy.

Zihao Zeng, Chubo Liu, Zhuo Tang, Wanli Chang, Kenli Li

Proceedings of the 58th ACM/IEEE Design Automation Conference, 2021

2020

CoExe: An Efficient Co-execution Architecture for Real-Time Neural Network Services.

Chubo Liu, Kenli Li, Mingcong Song, Jiechen Zhao, Keqin Li, Tao Li, Zihao Zeng

Proceedings of the 57th ACM/IEEE Design Automation Conference, 2020

2019

K-Means Parallel Acceleration for Sparse Data Dimensions on Flink.

Zihao Zeng, Kenli Li, Mingxing Duan, Chubo Liu, Xiangke Liao

Proceedings of the 21st IEEE International Conference on High Performance Computing and Communications; 17th IEEE International Conference on Smart City; 5th IEEE International Conference on Data Science and Systems, 2019