Chaoya Jiang

4

Papers

129

Total Citations

Papers (4)

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization

TiMix: Text-Aware Image Mixing for Effective Vision-Language Pre-training

BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.