Yitian Zhang

GmNet: Revisiting Gating Mechanisms From A Frequency View

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense

Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks

ARGen-Dexion: Autoregressive Image Generation Made Stronger by Vision Decoder

CompSRT: Quantization and Pruning for Image Super Resolution Transformers

Boosting Large Language Models with Mask Fine-Tuning

I$^2$BQ: Quantizing LLMs via Intra- and Inter-Block Optimization

Accessing Vision Foundation Models via ImageNet-1K

The Indra Representation Hypothesis

Scale-Free Graph-Language Models