5 papers
ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks
Haozhe Lu, Jiaqi Li, Xinyuan Zhu +1
Retrieval-Augmented Generation (RAG) can ground large language model (LLM) outputs in external evidence, but it also exposes the system to knowledge poisoning. Representative attac…
An agentic framework for gravitational-wave counterpart association in the multi-messenger era
Yiming Dong, Yacheng Kang, Junjie Zhao +3
With the detection of gravitational waves (GWs), multi-messenger astronomy has opened a new window for advancing our understanding of astrophysics, dense matter, gravitation, and c…
PPBoost: Progressive Prompt Boosting for Text-Driven Medical Image Segmentation
Xuchen Li, Hengrui Gu, Mohan Zhang +6
Text-prompted foundation models for medical image segmentation offer an intuitive way to delineate anatomical structures from natural language queries, but their predictions often…
Transform Before You Query: A Privacy-Preserving Approach for Vector Retrieval with Embedding Space Alignment
Ruiqi He, Zekun Fei, Jiaqi Li +5
Vector Database (VDB) can efficiently index and search high-dimensional vector embeddings from unstructured data, crucially enabling fast semantic similarity search essential for m…
Mind the Domain Gap: Measuring the Domain Gap Between Real-World and Synthetic Point Clouds for Automated Driving Development
Nguyen Duc, Yan-Ling Lai, Patrick Madlindl +5
Owing to the typical long-tail data distribution issues, simulating domain-gap-free synthetic data is crucial in robotics, photogrammetry, and computer vision research. The fundame…