Transformers have become the foundation of numerous state-of-the-art AI models across diverse domains, thanks to their powerful attention mechanism for modeling long-range dependencies. However, the quadratic scaling complexity of attention poses significant challenges for efficient hardware implementation. While techniques such as quantization and pruning help mitigate this issue, selective token attention offers a promising alternative by narrowing the attention scope to only the most relevant tokens, reducing computation and filtering out noise.In this work, we propose SATA, a locality-centric dynamic scheduling scheme that proactively manages sparsely distributed access patterns from selective Query-Key operations. By reordering operand flow and exploiting data locality, our approach enables early fetch and retirement of intermediate Query/Key vectors, improving system utilization. We implement and evaluate our token management strategy in a control and compute system, using runtime traces from selective-attention-based models. Experimental results show that our method improves system throughput by up to 1.76× and boosts energy efficiency by 2.94×, while incurring minimal scheduling overhead.

Vector Symbolic Architectures (VSAs), also known as hyperdimensional (HD) computing, are increasingly deployed in cognitive applications due to their simple and efficient operations. The widespread adoption has, in turn, spurred the development of a diverse set of hardware solutions that optimize VSA performance for embedded and edge AI systems. Despite these advances, there remains a lack of comprehensive, unified discussion on the co-design and co-evolution of VSA algorithms and hardware. This survey aims at bridging that gap by linking theoretical, software-level explorations with efficient hardware architectures and emerging technology fabrics for VSAs, providing co-design insights that are accessible to both algorithm and hardware communities. First, we introduce the principles of vector-symbolic computing, including its core mathematical operations and learning paradigms. Second, we provide an in-depth discussion on hardware technologies for VSAs, analyzing analog, mixed-signal, and digital circuit design styles. We compare hardware implementations of VSAs by carrying out detailed analysis of their performance characteristics and tradeoffs, from which we distill design guidelines that are applicable across arbitrary VSA formulations. Third, we discuss a methodology for cross-layer design of VSAs that identifies synergies across layers and explores key ingredients for hardware/software co-design of VSAs. Finally, as a concrete case study of this methodology, we present an in-memory computing hardware design for VSA-based hierarchical cognition, illustrating how the proposed co-design principles translate into efficient architectures. The article concludes with a discussion of open research challenges and opportunities for future explorations.

Accurate 2D human pose estimation from images is vital for understanding human actions. However, deploying the latest models, e.g., regression-based models, on resource-limited devices remains challenging due to their high computational requirements. In this paper, we address the resolution dilemma in regression-based multiperson pose estimation, where low-resolution inputs cause performance degradation, while high-resolution inputs drastically increase computational costs. To achieve a lightweight regression approach, it becomes crucial to enhance the model's capabilities in low-resolution scenarios. We propose the staggered alignment self-distillation (SASD) method and a corresponding network architecture. Our approach involves training two twin networks with shared weights: a high-resolution network and a low-resolution network. The high-resolution network serves as a teacher, guiding the learning process of the low-resolution network through feature map staggered alignment. The knowledge from the high-resolution network enhances the performance of the low-resolution network during low-resolution inference. Additionally, we employ a normalized skeleton loss to capture the loss of bone-related structure during training. Through extensive experiments on the MS-COCO and CrowdPose datasets, we demonstrate the superiority of our proposed method over state-of-the-art, lightweight multiperson pose estimation techniques, achieving much better performance with lower computational costs. Furthermore, our method achieves comparable performance to recent advanced regression-based pose estimation methods but with only 1/4 of the computational cost.

Most current image-level weakly supervised semantic segmentation (WSSS) methods are based on class activation map (CAM). However, the main limitation of weakly supervised semantic segmentation is that the CAMs generated by the WSSS network always focus on the most discriminative parts of the object, limiting the CAM to capture the holistic object. So we propose an average activation network to generate CAMs of the holistic object with weakly supervision. We restrain the highest activation regions of the CAM by continuously splitting the training image on the maximum activation point of the CAM during the training process. In this way, our network pays more attention to the whole of the object. In addition, we propose a CAM similarity loss function to narrow the gap between fully-supervised semantic segmentation (FSSS) and WSSS. We conducted experiments on the PASCAL VOC 2012 dataset to validate the effectiveness of our method.