Multi-class unsupervised anomaly detection (UAD) is challenging due to the difficulty of harmonizing distributional differences across categories within a unified framework. While recent diffusion-based methods have demonstrated promising performance by leveraging denoising processes for anomaly reconstruction, the lack of explicit causal constraints limits their ability to handle complex logical inconsistencies. Inspired by the success of autoregressive models in enforcing local-to-global logical consistency, we propose a Control-driven Autoregressive Reconstruction with Decoupled learning (CARD) framework for multi-class UAD. It first tokenizes images using vector quantization and employs a vision autoregressive model to capture causal dependencies within normal patterns as explicit prior knowledge. Then, we introduce a Control-Driven Reconstruction (CDR) network, which aligns input features as control signals into the frozen autoregressive model to adjust the predicted distribution, enabling a generative reconstruction process. Additionally, we apply perturbations to the CDR input to simulate anomalous conditions, facilitating the model to correct out-of-distribution anomaly features under prior knowledge constraints. By decoupling normal pattern learning from reconstruction, CARD prevents identity mapping caused by forgetting implicit priors in the conventional reconstruction-based method. Comprehensive experiments on several benchmark datasets validate the effectiveness of our approach. On the MVTecAD dataset, CARD achieved AUROC scores of 98.7% at the image level and 98.5% at the pixel level.

Object goal visual navigation is a challenging task that aims to guide a robot to find the target object based on its visual observation, and the target is limited to the classes pre-defined in the training stage. However, in real households, there may exist numerous target classes that the robot needs to deal with, and it is hard for all of these classes to be contained in the training stage. To address this challenge, we study the zero-shot object goal visual navigation task, which aims at guiding robots to find targets belonging to novel classes without any training samples. To this end, we also propose a novel zero-shot object navigation framework called semantic similarity network (SSNet). Our framework use the detection results and the cosine similarity between semantic word embeddings as input. Such type of input data has a weak correlation with classes and thus our framework has the ability to generalize the policy to novel classes. Extensive experiments on the AI2-THOR platform show that our model outperforms the baseline models in the zero-shot object navigation task, which proves the generalization ability of our model. Our code is available at: https://github.com/pioneer-innovation/Zero-Shot-Object-Navigation.