Search Results for author: Zihao Zheng

Found 15 papers, 7 papers with code

FedHQ: Hybrid Runtime Quantization for Federated Learning

no code implementations17 May 2025 Zihao Zheng, Ziyao Wang, Xiuping Cui, Maoliang Li, Jiayu Chen, Yun, Liang, Ang Li, Xiang Chen

However, many studies fail to consider the distinct performance attribution between particular quantization strategies, such as post-training quantization (PTQ) or quantization-aware training (QAT).

Federated Learning Quantization

MoQa: Rethinking MoE Quantization with Multi-stage Data-model Distribution Awareness

no code implementations27 Mar 2025 Zihao Zheng, Xiuping Cui, Size Zheng, Maoliang Li, Jiayu Chen, Yun, Liang, Xiang Chen

However, their analysis is designed for dense LLMs and relies on the simple one-model-all-data mapping, which is unsuitable for MoEs.

Language Modeling Language Modelling +2

Test Time Training for 4D Medical Image Interpolation

1 code implementation4 Feb 2025 Qikang Zhang, Yingjie Lei, Zihao Zheng, Ziyang Chen, Zhonghao Xie

Our method not only advances 4D medical image interpolation but also provides a template for domain adaptation in other fields such as image segmentation and image registration.

Diagnostic Domain Adaptation +4

RaSeRec: Retrieval-Augmented Sequential Recommendation

1 code implementation24 Dec 2024 Xinping Zhao, Baotian Hu, Yan Zhong, Shouzheng Huang, Zihao Zheng, Meng Wang, Haofen Wang, Min Zhang

Although prevailing supervised and self-supervised learning (SSL)-augmented sequential recommendation (SeRec) models have achieved improved performance with powerful neural network architectures, we argue that they still suffer from two limitations: (1) Preference Drift, where models trained on past data can hardly accommodate evolving user preference; and (2) Implicit Memory, where head patterns dominate parametric learning, making it harder to recall long tails.

Retrieval +2

Threshold Neuron: A Brain-inspired Artificial Neuron for Efficient On-device Inference

no code implementations18 Dec 2024 Zihao Zheng, Yuanchun Li, Jiayu Chen, Peng Zhou, Xiang Chen, Yunxin Liu

Enhancing the computational efficiency of on-device Deep Neural Networks (DNNs) remains a significant challengein mobile and edge computing.

Computational Efficiency Edge-computing

Infinite-Dimensional Feature Interaction

no code implementations22 May 2024 Chenhui Xu, Fuxun Yu, Maoliang Li, Zihao Zheng, Zirui Xu, JinJun Xiong, Xiang Chen

The past neural network design has largely focused on feature representation space dimension and its capacity scaling (e. g., width, depth), but overlooked the feature interaction space scaling.

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

1 code implementation13 May 2024 Haoran Li, Yulin Chen, Zihao Zheng, Qi Hu, Chunkit Chan, Heshan Liu, Yangqiu Song

We initially propose Overwrite Supervised Fine-tuning (OSFT) for effective backdoor removal when the trigger is known.

Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation

1 code implementation16 Aug 2023 Xinshuo Hu, Dongfang Li, Baotian Hu, Zihao Zheng, Zhenyu Liu, Min Zhang

To evaluate the effectiveness of our approach in terms of truthfulness and detoxification, we conduct extensive experiments on LLMs, encompassing additional abilities such as language modeling and mathematical reasoning.

Language Modeling Language Modelling +1

CKBP v2: Better Annotation and Reasoning for Commonsense Knowledge Base Population

1 code implementation20 Apr 2023 Tianqing Fang, Quyet V. Do, Zihao Zheng, Weiqi Wang, Sehyun Choi, Zhaowei Wang, Yangqiu Song

We show that CKBP v2 serves as a challenging and representative evaluation dataset for the CSKB Population task, while its development set aids in selecting a population model that leads to improved knowledge acquisition for downstream commonsense reasoning.

Knowledge Base Population Question Answering

VEM$^2$L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion

no code implementations4 Jul 2022 Tao He, Ming Liu, Yixin Cao, Tianwen Jiang, Zihao Zheng, Jingrun Zhang, Sendong Zhao, Bing Qin

In this paper, we solve the sparse KGC from these two motivations simultaneously and handle their respective drawbacks further, and propose a plug-and-play unified framework VEM$^2$L over sparse KGs.

Knowledge Distillation Missing Elements +1

DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension

no code implementations26 Apr 2021 Jiaqi Li, Ming Liu, Zihao Zheng, Heng Zhang, Bing Qin, Min-Yen Kan, Ting Liu

Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC.

Graph Neural Network Machine Reading Comprehension +1

An Annotation Scheme of A Large-scale Multi-party Dialogues Dataset for Discourse Parsing and Machine Comprehension

no code implementations8 Nov 2019 Jiaqi Li, Ming Liu, Bing Qin, Zihao Zheng, Ting Liu

In this paper, we propose the scheme for annotating large-scale multi-party chat dialogues for discourse parsing and machine comprehension.

Discourse Parsing Machine Reading Comprehension

Cannot find the paper you are looking for? You can Submit a new open access paper.