36 citations · 67 across the 35 of their papers we have counts for
37 papers
Rewriting or Reweighting? A Geometric Account in Language Models
Juntong Wang, Shengkun Yang, Xiyuan Wang +1
Post-training can substantially alter language-model behavior, yet aggregate behavior rates do not reveal whether training removes an existing mechanism, creates a new one, or chan…
CrossFlow: One-Step Generation Across Latent and Pixel Spaces
Xiyuan Wang, Xiao Zhang, Yang Li +4
Most diffusion and flow-matching generators define the prior, probability path, and prediction target in the same representation space. Latent diffusion improves efficiency by movi…
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
Juntong Wang, Haoyue Zhao, guanghui Pan +4
Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits the…
Position: How can Graphs Help Large Language Models?
Xiyuan Wang, Yi Hu, Yanbo Wang +2
With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding of textual features, more eff…
GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
Juntong Wang, Libin Chen, Xiyuan Wang +4
Repository-level bug localization-the task of identifying where code must be modified to fix a bug-is a critical software engineering challenge. Standard Large Language Modles (LLM…
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
Yewei Liu, Xiyuan Wang, Yansheng Mao +4
We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapters for large language models (LL…
Diffusion As Self-Distillation: End-to-End Latent Diffusion In One Model
Xiyuan Wang, Muhan Zhang
Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages.…
GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning
Weishuo Ma, Yanbo Wang, Xiyuan Wang +2
Graph Neural Networks (GNNs) are powerful tools for processing relational data but often struggle to generalize to unseen graphs, giving rise to the development of Graph Foundation…
Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs
Lecheng Kong, Xiyuan Wang, Yixin Chen +1
Large Language Models (LLMs) are emerging as versatile foundation models for computational chemistry, handling bidirectional tasks like reaction prediction and retrosynthesis. Howe…
Griffin: Towards a Graph-Centric Relational Database Foundation Model
Yanbo Wang, Xiyuan Wang, Quan Gan +4
We introduce Griffin, the first foundation model attemptation designed specifically for Relational Databases (RDBs). Unlike previous smaller models focused on single RDB tasks, Gri…
Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples
Sicong Han, Chenhao Lin, Zhengyu Zhao +6
Adversarial detection protects models from adversarial attacks by refusing suspicious test samples. However, current detection methods often suffer from weak generalization: their…
Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning
Yewei Liu, Xiyuan Wang, Muhan Zhang
We propose an entirely new meta-learning framework for network pruning. It is a general framework that can be theoretically applied to almost all types of networks with all kinds o…
OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction
Juntong Wang, Xiyuan Wang, Muhan Zhang
Common Neighbors (CNs) and their higher-order variants are important pairwise features widely used in state-of-the-art link prediction methods. However, existing methods often stru…
Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?
Xiyuan Wang, Yewei Liu, Lexi Pang +2
Diffusion models have gained popularity in graph generation tasks; however, the extent of their expressivity concerning the graph distributions they can learn is not fully understo…
Using Random Noise Equivariantly to Boost Graph Neural Networks Universally
Xiyuan Wang, Muhan Zhang
Recent advances in Graph Neural Networks (GNNs) have explored the potential of random noise as an input feature to enhance expressivity across diverse tasks. However, naively incor…
LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning
Yansheng Mao, Yufei Xu, Jiaqi Li +5
Long-context understanding remains challenging for LLMs due to limited context windows. This paper introduces Long Input Fine-Tuning (LIFT), a framework that improves the long-cont…
Exact Acceleration of Subgraph Graph Neural Networks by Eliminating Computation Redundancy
Qian Tao, Xiyuan Wang, Muhan Zhang +3
Graph neural networks (GNNs) have become a prevalent framework for graph tasks. Many recent studies have proposed the use of graph convolution methods over the numerous subgraphs o…
GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model
Haotong Yang, Xiyuan Wang, Qian Tao +3
Recent research on integrating Large Language Models (LLMs) with Graph Neural Networks (GNNs) typically follows two approaches: LLM-centered models, which convert graph data into t…
Reconsidering the Performance of GAE in Link Prediction
Weishuo Ma, Yanbo Wang, Xiyuan Wang +1
Recent advancements in graph neural networks (GNNs) for link prediction have introduced sophisticated training techniques and model architectures. However, reliance on outdated bas…
Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors
Junru Zhou, Cai Zhou, Xiyuan Wang +2
A popular way to improve the expressive power of graph neural networks (GNNs) is to use Laplacian eigenvectors as additional node features, since they can serve both as structural…
Geometric Representation Condition Improves Equivariant Molecule Generation
Zian Li, Cai Zhou, Xiyuan Wang +2
Recent advances in molecular generative models have demonstrated great promise for accelerating scientific discovery, particularly in drug design. However, these models often strug…
Efficient Neural Common Neighbor for Temporal Graph Link Prediction
Xiaohui Zhang, Yanbo Wang, Xiyuan Wang +1
Temporal graphs are widespread in real-world applications such as social networks, as well as trade and transportation networks. Predicting dynamic links within these evolving grap…
Graph as Point Set
Xiyuan Wang, Pan Li, Muhan Zhang
Graph is a fundamental data structure to model interconnections between entities. Set, on the contrary, stores independent elements. To learn graph representations, current Graph N…
On the Completeness of Invariant Geometric Deep Learning Models
Zian Li, Xiyuan Wang, Shijia Kang +1
Invariant models, one important class of geometric deep learning models, are capable of generating meaningful geometric representations by leveraging informative geometric features…