Yuxuan Si — accepted AI-conference papers

2026

CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution

Baoliang Tian, Yuxuan Si, Jilong Wang, LingYao Li, Zhongyuan Bao, Zineng Zhou +10

AAAI 2026technical

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual cues often conflict, requiring models to perform structured

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Think Then Rewrite: Reasoning Enhanced Query Rewriting for Domain Specific Retrieval

Ang Li, Yufei Shi, Yuxuan Si, Yiquan Wu, Ming Cai, Xu Tan +4

AAAI 2026technical

Query rewriting is a crucial task for improving retrieval, especially in professional domains such as law and medicine, where user queries are often underspecified and ambiguous. While large language models (LLMs) offer strong understanding and generation capabilities, existing LLM-based approaches

Cited by 0 Source ↗PDF ↗Scholar ↗