MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

Yanqi Dai, Huanran Hu, Lei Wang, Shengjie Jin, Xu Chen +1 more
2/12/2026

No official code found. Best implementation: YanqiDai/MMRole (101 stars, MIT, last commit 2026-02-02).

Semantic Scholar

Code Implementations(1)

YanqiDai/MMRoleCommunity76%
MIT

[ICLR 2025] A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

1014Shell, PythonJul 26, 20248 months agoMIT
benchmarklarge-multimodal-modelsrole-playing

Similar Papers

Balancing Risk and Reward: A Batched-Bandit Strategy for Automated Phased Release

99% match2026

Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives

99% match1 repo542026

MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers

99% match2026

KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations

98% match1 repo82026

CaKDP: Category-Aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection

98% match1 repo192026

Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation

98% match2026

Cite this paper

@article{dai2026mmrole,
  title  = {MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents},
  author = {Yanqi Dai and Huanran Hu and Lei Wang and Shengjie Jin and Xu Chen and Zhiwu Lu},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:4d567080294013a63149f3782ca67c4a9d346194},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/4d567080294013a63149f3782ca67c4a9d346194.svg)](https://codeofpaper.com/paper/4d567080294013a63149f3782ca67c4a9d346194)

Discussion