From the 1 of 17 linked papers with an AI index.
8 papers · 1 filter
DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
Bo Ye, Xinyu Cui, Jian Zhao +2
Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks…
KeepLoRA++: Continual Learning with Layer-Scaled Residual Gradient Adaptation
Mao-Lin Luo, Yi-Lin Zhang, Zi-Hao Zhou +5
Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of le…
SHED: Style-Homogenized Embedding Alignment for Domain Generalization
Kai Gan, Tong Wei
Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong…
Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery
Bo Ye, Kai Gan, Tong Wei +1
Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonl…
KeepLoRA: Continual Learning with Residual Gradient Adaptation
Mao-Lin Luo, Zi-Hao Zhou, Yi-Lin Zhang +3
Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of le…
Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition
Wei Tang, Zuo-Zheng Wang, Kun Zhang +2
Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased…