Author

Di-Hang Yang

h-index 0 View on Semantic Scholar

We have 2 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Sep 2026

CMJU: cross-modal joint unlearning for balanced forgetting in multimodal large language models

Cross-modal joint unlearning (CMJU) is proposed, a unified framework for balanced cross-modal forgetting that achieves better cross-modal forgetting balance than strong baselines, while maintaining competitive retain-set performance.

Di-Hang Yang, Bao-Chen Xiong, Xiaoshan Yang · Visual Intelligence · 0 citations

#natural language process... Preprint Sep 2026

CreaMem: A Scene-Aware Memory Architecture for Personalized Agents

The CreaMem architecture is proposed, which enables scene-aware memory organization by partitioning memory into several Life Scene Memories to reduce cross-scene interference at retrieval and improve QA accuracy across all evaluation metrics.

Qi-Xuan Sun, Yue Que, Bowei He et al. · 0 citations