Deep convolutional neural networks have a large number of parameters and require a significant number of floating-point operations during computation, which limits their deployment in situations where the storage space is limited and computational resources are insufficient, such as in mobile phones and small robots. Many network compression methods have been proposed to address the aforementioned issues, including pruning, low-rank decomposition, quantization, etc. However, these methods typically fail to achieve a significant compression ratio in terms of the parameter count. Even when high compression rates are achieved, the network’s performance is often significantly deteriorated, making it difficult to perform tasks effectively. In this study, we propose a more compact representation for neural networks, named Quantized Low-Rank Tensor Decomposition (QLTD), to super compress deep convolutional neural networks. Firstly, we employed low-rank Tucker decomposition to compress the pre-trained weights. Subsequently, to further exploit redundancies within the core tensor and factor matrices obtained through Tucker decomposition, we employed vector quantization to partition and cluster the weights. Simultaneously, we introduced a self-attention module for each core tensor and factor matrix to enhance the training responsiveness in critical regions. The object identification results in the CIFAR10 experiment showed that QLTD achieved a compression ratio of 35.43×, with less than 1% loss in accuracy and a compression ratio of 90.61×, with less than a 2% loss in accuracy. QLTD was able to achieve a significant compression ratio in terms of the parameter count and realize a good balance between compressing parameters and maintaining identification accuracy.
World models (WMs) provide a unified approach for modeling how environments evolve over time by learning predictive representations of states and observations. Recent advances in large-scale generative modeling and multimodal foundation models have substantially broadened their applicability across a wide range of interactive and multimodal domains; however, existing research remains fragmented across modeling paradigms, application domains, and evaluation protocols. This survey provides a systematic and in-depth review of WMs in artificial intelligence. Based on the world modeling paradigms of existing methods, we first categorize WMs into four branches with formal mathematical formulations: observation-level generative, latent space, reinforcement learning-based, and object-centric WMs. We further review a broad range of WM applications spanning robotics, autonomous driving, scientific discovery, game simulation, GUI-based agents, as well as interpretability and trustworthiness, and analyze benchmarks, new evaluation metrics, simulation platforms, and comparative results across WMs. Finally, we discuss key challenges, including long-horizon consistency, and generalization, and outline promising directions for future research. This survey provides an actively updated \href{https://github.com/JiahuaDong/Awesome-World-Models}{GitHub Repository} to track developments in WMs and aims to offer a unified reference for understanding, comparing, and advancing WMs.
In this paper, we apply kernel methods to deep convolutional neural network (DCNN) to improve its nonlinear ability. DCNNs have achieved significant improvement in many computer vision tasks. For an image classification task, the accuracy comes to saturation when the depth and width of network are enough and appropriate. The saturation accuracy will not rise even by increasing the depth and width. We find that improving nonlinear ability of DCNNs can break through the saturation accuracy. In a DCNN, the former layer is more inclined to extract features and the latter layer is more inclined to classify features. Therefore, we apply kernel methods at the last fully connected layer to implicitly map features to a higher-dimensional space to improve nonlinear ability so that the network achieves better linear separability. Also, we name the network as fully kernected neural networks (fully connected neural networks with kernel methods). Our experiment result shows that fully kernected neural networks achieve higher classification accuracy and faster convergence rate than baseline networks.
Continual video instance segmentation demands both the plasticity to absorb new object categories and the stability to retain previously learned ones, all while preserving temporal consistency across frames. In this work, we introduce Contrastive Residual Injection and Semantic Prompting (CRISP), an earlier attempt tailored to address the instance-wise, category-wise, and task-wise confusion in continual video instance segmentation. For instance-wise learning, we model instance tracking and construct instance correlation loss, which emphasizes the correlation with the prior query space while strengthening the specificity of the current task query. For category-wise learning, we build an adaptive residual semantic prompt (ARSP) learning framework, which constructs a learnable semantic residual prompt pool generated by category text and uses an adjustive query-prompt matching mechanism to build a mapping relationship between the query of the current task and the semantic residual prompt. Meanwhile, a semantic consistency loss based on the contrastive learning is introduced to maintain semantic coherence between object queries and residual prompts during incremental training. For task-wise learning, to ensure the correlation at the inter-task level within the query space, we introduce a concise yet powerful initialization strategy for incremental prompts. Extensive experiments on YouTube-VIS-2019 and YouTube-VIS-2021 datasets demonstrate that CRISP significantly outperforms existing continual segmentation methods in the long-term continual video instance segmentation task, avoiding catastrophic forgetting and effectively improving segmentation and classification performance. The code is available at https://github.com/01upup10/CRISP.