4 papers · 1 filter
FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
Hang Guo, Yawei Li, Taolin Zhang +4
Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale s…
BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping
Taolin Zhang, Jinpeng Wang, Hang Guo +3
Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of…
ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
Hang Guo, Tao Dai, Zhihao Ouyang +4
Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded withi…
Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach
Taolin Zhang, Jiawang Bai, Zhihe Lu +4
Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable…