activity
20242026
collaborators

17 papers

cs.AI2026

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…

cs.CL2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…