Towards Customized Multimodal Role-Play
Unified multimodal understanding and generation models enable richer human-AI interaction. Yet jointly customizing a character's persona, dialogue style, and visual identity while maintaining output consistency across modalities remains largely unexplored. To mitigate this gap, we introduce a new task, Customized Multimodal Role-Play (CMRP). We construct the RoleScape-20 dataset comprising 20 characters, including training and evaluation data that cover persona, stylistic descriptions, visual/expressive cues, and text-image interactions. Building on a unified model, we devise UniCharacter, a two-stage training framework containing Unified Supervised Finetuning (Unified-SFT) and character-...
| Authors | Chao Tang, Jianzong Wu, Qingyu Shi et al. |
|---|---|
| Primary category | cs.LG |
| Published | 1 May 2026 |
| Last updated at source | 1 May 2026 |
Connected in the knowledge graph
- Tangc03/RoleScape20Dataset · cited by
Models and datasets referencing this paper
- Tangc03/RoleScape20Dataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.