5 papers
KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls
Kailin Jiang, Hongbo Jiang, Ning Jiang +7
Large Multimodal Models encode extensive factual knowledge in their pre-trained weights. However, its knowledge remains static and limited, unable to keep pace with real-world deve…
Can Unified Generation and Understanding Models Maintain Semantic Equivalence Across Different Output Modalities?
Hongbo Jiang, Jie Li, Yunhang Shen +4
Unified Multimodal Large Language Models (U-MLLMs) integrate understanding and generation within a single architecture. However, existing evaluations typically assess these capabil…
Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation
Hongbo Jiang, Jie Li, Xinqi Cai +4
Practical cloud-edge deployment of Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models for diverse modali…
Insert Anything: Image Insertion via In-Context Editing in DiT
Wensong Song, Hong Jiang, Zongxing Yang +2
This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexib…
ElaLoRA: Elastic & Learnable Low-Rank Adaptation for Efficient Model Fine-Tuning
Huandong Chang, Zicheng Ma, Mingyuan Ma +4
Low-Rank Adaptation (LoRA) has become a widely adopted technique for fine-tuning large-scale pre-trained models with minimal parameter updates. However, existing methods rely on fi…