Xinyu Gao

collaborators

7 papers

cs.CL2026

Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs

Xinyu Gao, Shaonan Wang, Nai Ding

Decoder-only large language models achieve strong broad performance but are brittle to minor grammatical perturbations, undermining reliability for downstream reasoning. However, d…

cs.CL2026

Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective

Yunhao Liu, Zian Jia, Xinyu Gao +2

Retrieval-Augmented Generation (RAG) effectively grounds Large Language Models (LLMs) with external knowledge and is widely applied to Web-related tasks. However, its scalability i…

math.CA2026

Lebesgue bounds for multilinear spherical and lacunary maximal averages

Xinyu Gao

We establish $L^{p_{1}} (R^{d}) \times \dots \times L^{p_{n}} (R^{d}) \to L^{r} (R^{d})$ bounds for spherical averaging operators $A^{n}$ in dimensions $d…

math.CA2026

A.E. Convergence vs Boundedness

Xinyu Gao, Loukas Grafakos

We extend Stein's maximal theorem to the bilinear setting. Let $M$ be a homogeneous space with a transitive action of a compact abelian group, and let $1 \leq p, q \leq 2$ and $1/2 \l…

cs.AI2026

TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion

Xinyu Gao

Knowledge Graphs have become fundamental infrastructure for applications such as intelligent question answering and recommender systems due to their expressive representation. Neve…

cs.CR2025

DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation

Xinyu Gao, Xiangtao Meng, Yingkai Dong +2

While Retrieval-Augmented Generation (RAG) effectively reduces hallucinations by integrating external knowledge bases, it introduces vulnerabilities to membership inference attacks…