Research map / Large language models / Language, safety and interpretability
Personalized Visual Content Generation in Conversational Systems
Xianquan Wang, Zhaocheng Du, Huibo Xu, Shukang Yin, Yupeng Han, Jieming Zhu, Kai Zhang, Qi Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces PCG, a framework for personalized visual content generation within conversational systems, aiming to replace one-size-fits-all recommendations with user-tailored generated images.
Problem
Current conversational systems present the same recommended content to all users ("one-size-fits-all"), limiting personalization and user engagement.
Approach
Generates personalized visual content inside conversations by combining LLMs and diffusion models so that the generated content adapts to each user; the abstract is truncated so the specific mechanism is not stated.
Closest papers by meaning
- Contextualized Visual Personalization in Vision-Language Models (ICML 2026 · similarity 0.88)
- MMPB: It’s Time for Multi-Modal Personalization (NeurIPS 2025 · similarity 0.87)
- VisualLens: Personalization through Task-Agnostic Visual History (NeurIPS 2025 · similarity 0.87)
- MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation (AAAI 2026 · similarity 0.87)
- Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond (ICLR 2024 · similarity 0.87)
- Yo'Chameleon: Personalized Vision and Language Generation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
