6 papers
OptiSQL: Executable SQL Generation from Optical Tokens
Sifan Li, Hongkai Chen, Yujun Cai +3
Executable SQL generation is typically studied in text-to-SQL settings, where tables are provided as fully linearized textual schemas and contents. While effective, this formulatio…
Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector
Sifan Li, Hongkai Chen, Yujun Cai +4
Vision Language Models (VLMs) have achieved impressive progress in multimodal reasoning; yet, they remain vulnerable to hallucinations, where outputs are not grounded in visual evi…
Detecting and Mitigating Insertion Hallucination in Video-to-Audio Generation
Liyang Chen, Hongkai Chen, Yujun Cai +3
Video-to-Audio generation has made remarkable strides in automatically synthesizing sound for video. However, existing evaluation metrics, which focus on semantic and temporal alig…
SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
Sifan Li, Yujun Cai, Yiwei Wang
Vision-language models (VLMs) excel in semantic tasks but falter at a core human capability: detecting hidden content in optical illusions or AI-generated images through perceptual…
Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image
Sifan Li, Ming Tao, Hao Zhao +2
Text-to-Image (T2I) has been prevalent in recent years, with most common condition tasks having been optimized nicely. Besides, counterfactual Text-to-Image is obstructing us from…
Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs
Sifan Li, Yujun Cai, Bryan Hooi +2
Traditional Chinese Medicine (TCM) has seen increasing adoption in healthcare, with specialized Large Language Models (LLMs) emerging to support clinical applications. A fundamenta…