activity
20242026
most citedStructured Attention Matters to Multimodal LLMs in Document Understanding

1 citations · 1 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CL2026

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…

cs.CV2025

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…

cs.SD2025

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…

cs.AI2025

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning

Hang Wu, Hongkai Chen, Yujun Cai +4

Grounding natural language queries in graphical user interfaces (GUIs) poses unique challenges due to the diversity of visual elements, spatial clutter, and the ambiguity of langua…

cs.CL20251 cited

Structured Attention Matters to Multimodal LLMs in Document Understanding

Chang Liu, Hongkai Chen, Yujun Cai +4

Document understanding remains a significant challenge for multimodal large language models (MLLMs). While previous research has primarily focused on locating evidence pages throug…

cs.CV2024

Tri-Ergon: Fine-grained Video-to-Audio Generation with Multi-modal Conditions and LUFS Control

Bingliang Li, Fengyu Yang, Yuxin Mao +3

Video-to-audio (V2A) generation utilizes visual-only video features to produce realistic sounds that correspond to the scene. However, current V2A models often lack fine-grained co…