4 papers
MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents
Dannong Xu, Zhongyu Yang, Jun Chen +6
Multimodal large language models (MLLMs) achieve strong performance on benchmarks that evaluate text, image, or video understanding separately. However, these settings do not asses…
Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models
Zhongyu Yang, Dannong Xu, Wei Pang +1
The rapid growth of visual tokens in multimodal large language models (MLLMs) leads to excessive memory consumption and inference latency, especially when handling high-resolution…
WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation
Zhongyu Yang, Jun Chen, Dannong Xu +5
Knowledge discovery and collection are intelligence-intensive tasks that traditionally require significant human effort to ensure high-quality outputs. Recent research has explored…
Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
Jun Chen, Dannong Xu, Junjie Fei +2
Large multimodal models (LMMs) have achieved impressive progress in vision-language understanding, yet they face limitations in real-world applications requiring complex reasoning…