People
Publications
Resources
Contact
M. Zhang
Latest
GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models
Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors
HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention
Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs
Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
Expressive Graph Neural Networks via Equivariant Use of Noise
JurisBench: A Deep Benchmark for Assessing Large Language Models in Professional Legal Practice
Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation
Law in Silico: Simulating Legal Society with LLM-Based Agents
LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning
Position: How can Graphs Help Large Language Models?
Relational In-Context Learning via Synthetic Pre-training with Structural Prior
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding
Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures
VecMol: Vector-Field Representations for 3D Molecule Generation
Unified Modeling of 3D Molecular Generation via Atomic Interactions with PocketXMol
TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill & Decode Inference
Efficient Neural Common Neighbor for Temporal Graph Link Prediction
FLORA: GNNs as Predictors of Agentic Workflow Performances
Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs
LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation
Reconsidering the Performance of GAE in Link Prediction
Exact Acceleration of Subgraph Graph Neural Networks by Eliminating Computation Redundancy
CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning
Geometric Representation Condition Improves Equivariant Molecule Generation
Griffin: Towards a Graph-Centric Relational Database Foundation Model
3D-SubG: A 3D Stacked Hybrid Processing Near/In-Memory Accelerator for Subgraph GNNs
Parameter-Efficient and Stable Singular Value Adaptation for Pre-Trained Models
GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
Number Cookbook: Number Understanding of Language Models and How to Improve It
On the Completeness of Invariant Geometric Deep Learning Models
Improving Graph Neural Networks on Multi-node Tasks with the Labeling Trick
VACT: A Video Automatic Causal Testing System and a Benchmark
Cite
×