Get started
Author

Zhenhua Dong

Observed name: Dong, Zhenhua
Observed institution: Huawei Technologies (China)
ORCID: 0000-0002-2231-4663
Observed ORCID: 0000-0002-2231-4663
OpenAlex ID: A5121241366
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
2026 · Pengxiang Zhao, Hui-Ling Zhen, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1
PDF
How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing
2026 · Zhao, Pengxiang, Li, Xing, et al. · arXiv (Cornell University)
PDF
AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters
2026 · Qian, Yu-Yang, Wu, Hao-Cong, et al. · arXiv (Cornell University)
PDF
Towards Fast Domain Adaptation and Fine-Grained User Simulation for Evaluating Conversational Recommender Systems
2026 · Li, Yuanzi, Dai, Quanyu, et al. · arXiv (Cornell University)
PDF
QuantClaw: Precision Where It Matters for OpenClaw
2026 · Zhang, Manyi, Li, Ji-Fu, et al. · arXiv (Cornell University)
PDF
Optimizing Multi-Turn Interactive Recommendation Agents via Generative Intrinsic Motivation
2026 · Xueyang Feng, Jiakai Tang, et al. · International World Wide Web Conference (WWW)
HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
2026 · Zhu, Qihui, Zhang, Tao, et al. · arXiv (Cornell University)
PDF
EENet: An Efficient and Effective Network for Large-Scale CTR Prediction
2026 · Dezhi Yi, Bo Chen, et al. · ACM Transactions on Information Systems
Analyzing how pre-trained language models capture factual knowledge using attribution methods
2026 · Shaobo Li, Chengjie Sun, et al. · Knowledge-Based Systems
SwiftMem: Fast Agentic Memory via Query-aware Indexing
2026 · Tian, Anxin, Li, Yiming, et al. · arXiv (Cornell University)
PDF
What Matters For Safety Alignment?
2026 · Li, Xing, Zhen, Hui-Ling, et al. · arXiv (Cornell University)
PDF
BATQuant: Outlier-Resilient MXFP4 Quantization via Learnable Block-Wise Optimization
2026 · Ji-Fu Li, Manyi Zhang, et al. · Lecture notes in computer science
PDF
DPIFrame: A Dual-Level Parallelism Acceleration Framework for CTR Model Inference
2026 · Dezhi Yi, Huifeng Guo, et al. · IEEE Transactions on Computers
PDF
Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats
2026 · Manyi Zhang, Ji-Fu Li, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Towards Efficient Agents: A Co-Design of Inference Architecture and System
2025 · Lin, Weizhe, Zhen, Hui-Ling, et al. · arXiv (Cornell University)
PDF
CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning
2025 · Zhou, Yuqi, Wang, Shuai, et al. · arXiv (Cornell University)
PDF
Works count: 16
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type