17 papers
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
Xiaojie Li, Yibo Yang, Jianlong Wu +4
Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes from limited examples while preserving knowledge of previously learned classes. Existing metho…
Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation
Xuening Zhang, Qi Lv, Xiang Deng +3
View transformers process multi-view observations to predict actions and have shown impressive performance in robotic manipulation. Existing methods typically extract static visual…
TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models
Qianlong Xiang, Miao Zhang, Haoyu Zhang +3
Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful c…
GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning
Xiaojie Li, Bei Wang, Wei Liu +4
The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on…
MegaSR: Mining Customized Semantics and Expressive Guidance for Real-World Image Super-Resolution
Xinrui Li, Jinrong Zhang, Jianlong Wu +3
Text-to-image (T2I) models have ushered in a new era of real-world image super-resolution (Real-ISR) due to their rich internal implicit knowledge for multimodal learning. Although…
Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
Jiarui Jiang, Wei Huang, Miao Zhang +2
State-space models (SSMs), particularly Mamba, emerge as an efficient Transformer alternative with linear complexity for long-sequence modeling. Recent empirical works demonstrate…