3 papers
cs.AI2026
DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents
Zhuoran Yu, Le Thien Phuc Nguyen, Jaden Park +5
Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question answering. However, existing…
cs.CV2025
Composition-Grounded Data Synthesis for Visual Reasoning
Xinyi Gu, Jiayuan Mao, Zhang-Wei Hong +5
Pretrained multi-modal large language models (MLLMs) demonstrate strong performance on diverse multimodal tasks, but remain limited in reasoning capabilities for domains where anno…
cs.CV2025
Generating Fine Details of Entity Interactions
Xinyi Gu, Jiayuan Mao
Recent text-to-image models excel at generating high-quality object-centric images from instructions. However, images should also encapsulate rich interactions between objects, whe…