3 papers
cs.AI2026
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
Jianhao Chen, Shiqin Wang, Haoyang Chen +4
Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual perception with text generation. Existing multimodal jailbreak attacks primaril…
cs.IR2026
Scaling Multilingual Semantic Search in Uber Eats Delivery
Bo Ling, Zheng Liu, Haoyang Chen +3
We present a production-oriented semantic retrieval system for Uber Eats that unifies retrieval across stores, dishes, and grocery/retail items. Our approach fine-tunes a Qwen2 two…
cs.CL2025
Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking
Liangliang Zhang, Zhuorui Jiang, Hongliang Chi +8
Knowledge Graph Question Answering (KGQA) systems rely on high-quality benchmarks to evaluate complex multi-hop reasoning. However, despite their widespread use, popular datasets s…