Rui Yan

See the Text: From Tokenization to Visual Reading

R-Genie: Reasoning-Guided Generative Image Editing

Routing-Deconstructed LoRA in Federated Fine-Tuning

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

IMAGEdit: Let Any Subject Transform

Vision-centric Token Compression in Large Language Model

Memory Efficient Transformer Adapter for Dense Predictions

You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM

Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition