6 papers
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…
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…
Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
Haomiao Qiu, Miao Zhang, Ziyue Qiao +1
Continual Learning (CL) aims to enable models to continuously acquire new knowledge from a sequence of tasks with avoiding the forgetting of learned information. However, existing…
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
Jiarui Jiang, Wei Huang, Miao Zhang +2
Transformers have demonstrated great power in the recent development of large foundational models. In particular, the Vision Transformer (ViT) has brought revolutionary changes to…
DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture
Qianlong Xiang, Miao Zhang, Yuzhang Shang +3
Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effective…