2 papers
cs.AI2026
TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation
Jingyi Zheng, Yule Liu, Zifan Peng +4
Internet memes are a pervasive form of multimodal online communication; however, such communication often involves users from diverse linguistic and cultural backgrounds. Therefore…
cs.CL2026
AWM: Answerable Working Memory for Long-Document VQA Agents
Dongzhuoran Zhou, Yuqicheng Zhu, Yule Liu +5
Long-document visual question answering increasingly relies on VLM agents that retrieve candidate pages, inspect page images, write findings to working memory, and synthesize answe…