3 papers
cs.CV2025
Optimizing Vision-Language Consistency via Cross-Layer Regional Attention Alignment
Yifan Wang, Hongfeng Ai, Quangao Liu +7
Vision Language Models (VLMs) face challenges in effectively coordinating diverse attention mechanisms for cross-modal embedding learning, leading to mismatched attention and subop…
cs.CL2025
DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism
Dengchun Li, Naizheng Wang, Zihao Zhang +4
Instruction-based fine-tuning of large language models (LLMs) has achieved remarkable success in various natural language processing (NLP) tasks. Parameter-efficient fine-tuning (P…
cs.CV2024
Distribution-Aware Data Expansion with Diffusion Models
Haowei Zhu, Ling Yang, Jun-Hai Yong +5
The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeav…