62 citations · 72 across the 11 of their papers we have counts for
7 papers · 1 filter
Video Generation Models Are Good Latent Reward Models
Xiaoyue Mi, Wenqing Yu, Jiesong Lian +9
Reward feedback learning (ReFL) has proven effective for aligning image generation with human preferences. However, its extension to video generation faces significant challenges.…
Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
Shibo Jie, Yehui Tang, Jianyuan Guo +3
Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging sim…
Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Shibo Jie, Yehui Tang, Ning Ding +3
Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space…
Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
Shibo Jie, Haoqing Wang, Zhi-Hong Deng
Current state-of-the-art results in computer vision depend in part on fine-tuning large pre-trained vision models. However, with the exponential growth of model sizes, the conventi…
FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer
Shibo Jie, Zhi-Hong Deng
Recent work has explored the potential to adapt a pre-trained vision transformer (ViT) by updating only a few parameters so as to improve storage efficiency, called parameter-effic…
Convolutional Bypasses Are Better Vision Transformer Adapters
Shibo Jie, Zhi-Hong Deng
The pretrain-then-finetune paradigm has been widely adopted in computer vision. But as the size of Vision Transformer (ViT) grows exponentially, the full finetuning becomes prohibi…
Alleviating Representational Shift for Continual Fine-tuning
Shibo Jie, Zhi-Hong Deng, Ziheng Li
We study a practical setting of continual learning: fine-tuning on a pre-trained model continually. Previous work has found that, when training on new tasks, the features (penultim…