Zhiqiang Zhang

papers

132

total citations

papers (12)

MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data

NEURIPS 2021arXiv

citations

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

NEURIPS 2025arXiv

citations

Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation

AAAI 2025arXiv

citations

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

AAAI 2025arXiv

citations

K-ON: Stacking Knowledge on the Head Layer of Large Language Model

AAAI 2025arXiv

citations

MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models

ICML 2025arXiv

citations

Explore What LLM Does Not Know in Complex Question Answering

AAAI 2025

citations

Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning

ICML 2024

citations

HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multi-task Learning

AAAI 2025

citations

Zhiqiang Zhang

papers (12)

Bandit Samplers for Training Graph Neural Networks

Adversarially Robust Neural Architecture Search for Graph Neural Networks

Structural Information Enhanced Graph Representation for Link Prediction

MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

K-ON: Stacking Knowledge on the Head Layer of Large Language Model

MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models

Explore What LLM Does Not Know in Complex Question Answering

Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning

HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multi-task Learning

papers (12)

Bandit Samplers for Training Graph Neural Networks

Adversarially Robust Neural Architecture Search for Graph Neural Networks

Structural Information Enhanced Graph Representation for Link Prediction

MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

K-ON: Stacking Knowledge on the Head Layer of Large Language Model

MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models

Explore What LLM Does Not Know in Complex Question Answering

Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning

HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multi-task Learning