Chen Zhang, Bo Hu, Weidong Chen, Zhendong Mao
HistLLM: A Unified Framework for LLM-Based Multimodal Recommendation with User History Encoding and Compression
https://arxiv.org/abs/2504.10150

challenge, we introduce HistLLM, an innovative multimodal recommendation framework that integrates textual and visual features through a User History Encoding Module (UHEM), compressing multimodal user history interactions into a single token [4/5 of https://arxiv.org/abs/2504.10150v1]

Chen Zhang, Bo Hu, Weidong Chen, Zhendong Mao: HistLLM: A Unified Framework for LLM-Based Multimodal Recommendation with User History Encoding and Compression https://arxiv.org/abs/2504.10150 https://arxiv.org/pdf/2504.10150 https://arxiv.org/html/2504.10150

AI struggles to interpret human history: The study, which is the first of its kind, evaluates the historical knowledge of leading AI models such as ChatGPT-4, Llama, and Gemini.

#AIHistoryChallenges #LLMLimitations #SeshatDatabank #HistLLM #AIResearch #EarthDotCom #EarthSnap #Earth