Muhan Zhang

papers

1,028

total citations

papers (21)

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

NEURIPS 2021arXiv

237

citations

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

NEURIPS 2025arXiv

citations

Geodesic Graph Neural Network for Efficient Graph Representation Learning

NEURIPS 2022arXiv

citations

An Empirical Study of Realized GNN Expressiveness

ICML 2024arXiv

citations

Is Distance Matrix Enough for Geometric Deep Learning?

NEURIPS 2023arXiv

citations

Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes

NEURIPS 2023arXiv

citations

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman

NEURIPS 2023arXiv

citations

Rethinking Knowledge Graph Evaluation Under the Open-World Assumption

NEURIPS 2022arXiv

citations

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

NEURIPS 2023arXiv

citations

Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power

NEURIPS 2023arXiv

citations

Graph As Point Set

ICML 2024arXiv

citations

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs

NEURIPS 2025arXiv

citations

CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning

ICLR 2025arXiv

citations

CLOVER: Cross-Layer Orthogonal Vectors Pruning

ICML 2025arXiv

citations

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades

NEURIPS 2025arXiv

citations

OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction

NEURIPS 2025arXiv

citations

Muhan Zhang

papers (21)

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

Nested Graph Neural Networks

Decoupling the Depth and Scope of Graph Neural Networks

How Powerful are K-hop Message Passing Graph Neural Networks

Case-Based or Rule-Based: How Do Transformers Do the Math?

Number Cookbook: Number Understanding of Language Models and How to Improve It

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

Geodesic Graph Neural Network for Efficient Graph Representation Learning

An Empirical Study of Realized GNN Expressiveness

Is Distance Matrix Enough for Geometric Deep Learning?

Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman

Rethinking Knowledge Graph Evaluation Under the Open-World Assumption

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power

Graph As Point Set

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs

CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning

CLOVER: Cross-Layer Orthogonal Vectors Pruning

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades

OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction

papers (21)

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

Nested Graph Neural Networks

Decoupling the Depth and Scope of Graph Neural Networks

How Powerful are K-hop Message Passing Graph Neural Networks

Case-Based or Rule-Based: How Do Transformers Do the Math?

Number Cookbook: Number Understanding of Language Models and How to Improve It

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

Geodesic Graph Neural Network for Efficient Graph Representation Learning

An Empirical Study of Realized GNN Expressiveness

Is Distance Matrix Enough for Geometric Deep Learning?

Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman

Rethinking Knowledge Graph Evaluation Under the Open-World Assumption

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power

Graph As Point Set

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs

CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning

CLOVER: Cross-Layer Orthogonal Vectors Pruning

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades

OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction