Muhan Zhang

JurisBench: A Deep Benchmark for Assessing Large Language Models in Professional Legal Practice ACL 2026 Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation ACL 2026 SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding ACL 2026 Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures ACL 2026 CLOVER: Cross-Layer Orthogonal Vectors Pruning ICML 2025 Geometric Representation Condition Improves Equivariant Molecule Generation ICML 2025 GOFA: A Generative One-For-All Model for Joint Graph Language Modeling ICLR 2025 Griffin: Towards a Graph-Centric Relational Database Foundation Model ICML 2025 HD-PiSSA: High-Rank Distributed Orthogonal Adaptation EMNLP 2025 Improving Graph Neural Networks on Multi-node Tasks with the Labeling Trick JMLR 2025 Number Cookbook: Number Understanding of Language Models and How to Improve It ICLR 2025 On the Completeness of Invariant Geometric Deep Learning Models ICLR 2025 4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBs NeurIPS 2024 An Empirical Study of Realized GNN Expressiveness ICML 2024 Case-Based or Rule-Based: How Do Transformers Do the Math? ICML 2024 Graph As Point Set ICML 2024 LooGLE: Can Long-Context Language Models Understand Long Contexts? ACL 2024 Mars: Situated Inductive Reasoning in an Open-World Environment NeurIPS 2024 Neural Common Neighbor with Completion for Link Prediction ICLR 2024 One For All: Towards Training One Graph Model For All Classification Tasks ICLR 2024 On the Stability of Expressive Positional Encodings for Graphs ICLR 2024 PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models NeurIPS 2024 Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability ICLR 2024 RulE: Knowledge Graph Reasoning with Rule Embedding ACL 2024 Unifying Generation and Prediction on Graphs with Latent Graph Diffusion NeurIPS 2024 VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs ICLR 2024 Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs ICLR 2023 CktGNN: Circuit Graph Neural Network for Electronic Design Automation ICLR 2023 Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power NeurIPS 2023 Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman NeurIPS 2023 Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes NeurIPS 2023 From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks ICML 2023 Is Distance Matrix Enough for Geometric Deep Learning? NeurIPS 2023 MAG-GNN: Reinforcement Learning Boosted Graph Neural Network NeurIPS 2023 3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design ICML 2022 Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks ICLR 2022 Geodesic Graph Neural Network for Efficient Graph Representation Learning NeurIPS 2022 GLASS: GNN with Labeling Tricks for Subgraph Representation Learning ICLR 2022 How Powerful are K-hop Message Passing Graph Neural Networks NeurIPS 2022 How Powerful are Spectral Graph Neural Networks ICML 2022 PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs ICML 2022 Rethinking Knowledge Graph Evaluation Under the Open-World Assumption NeurIPS 2022 Decoupling the Depth and Scope of Graph Neural Networks NeurIPS 2021 Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning NeurIPS 2021 Nested Graph Neural Networks NeurIPS 2021 Inductive Matrix Completion Based on Graph Neural Networks ICLR 2020 D-VAE: A Variational Autoencoder for Directed Acyclic Graphs NeurIPS 2019 Link Prediction Based on Graph Neural Networks NeurIPS 2018