17 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…
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
Yewei Liu, Xiyuan Wang, Yansheng Mao +3
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…
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…
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…
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…
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…