papers

Publications (5)

cs.CR2026

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

Junchen Li, Chao Qi, Rongzheng Wang +7

Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing a…

cs.CV2025

RepText: Rendering Visual Text via Replicating

Haofan Wang, Yujia Xu, Yimeng Li +5

Although contemporary text-to-image generation models have achieved remarkable breakthroughs in producing visually appealing images, their capacity to generate precise and flexible…

cs.LG2026

Frequency-Domain Multi-Modality Transportation Modeling

Jiewen Deng, Hangchen Liu, Junchen Li +2

Multi-modality transportation refers to urban systems composed of multiple transportation modes, such as traffic flow and public transit, whose dynamics are coupled by shared tempo…

cs.CV2026

MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation

Ruiyao Liu, Hui Shen, Ping Zhang +16

Modern generative models have demonstrated the ability to solve challenging mathematical problems. In many real-world settings, however, mathematical solutions must be expressed vi…

cs.IR2025

NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval

Junchen Li, Rongzheng Wang, Yihong Huang +3

Retrieval-augmented generation (RAG) greatly enhances large language models (LLMs) performance in knowledge-intensive tasks. However, naive RAG methods struggle with multi-hop ques…