Retrieval-augmented generation (RAG) systems rely on large-scale embedding search. However, the growth of corpora and the demand for real-time queries expose the memory capacity and bandwidth limitations of DRAM-centric architectures. To address this challenge, we adopt CXL memory in conjunction with cluster-scale RAG deployments and optimize the system in terms of performance, latency and cost efficiency. Our design leverages state-of-the-art CXL memory devices and platforms with memory management policies such as weighted interleaving and tiering between DRAM and CXL memory. In comparison with a DRAM baseline, our system archives 20% higher vector search performance and 43% lower LLM time-to-first token (TTFT), demonstrating clear end-to-end performance benefits. Moreover, in the context of overall system efficiency, we observed up to 20% and 42% improvement in power efficiency (QPS/Watt) and cost efficiency (QPS/$), respectively. These results demonstrate that, despite the relatively high latency of CXL memory, memory management policy-level optimization enable CXL memory to serve as a first-class memory resource in cluster-based RAG systems.

Anomalous event detection in surveillance videos is a challenging and practical research problem among image and video processing community. Compared to the frame-level annotations of anomalous events, obtaining video-level annotations is quite fast and cheap though such high-level labels may contain significant noise. More specifically, an anomalous labeled video may actually contain anomaly only in a short duration while the rest of the video frames may be normal. In the current work, we propose a weakly supervised anomaly detection framework based on deep neural networks which is trained in a self-reasoning fashion using only video-level labels. To carry out the self-reasoning based training, we generate pseudo labels by using binary clustering of spatio-temporal video features which helps in mitigating the noise present in the labels of anomalous videos. Our proposed formulation encourages both the main network and the clustering to complement each other in achieving the goal of more accurate anomaly detection. The proposed framework has been evaluated on publicly available real-world anomaly detection datasets including UCF-crime, ShanghaiTech and UCSD Ped2. The experiments demonstrate superiority of our proposed framework over the current state-of-the-art methods.

This study examines the differential effects of hedonic vs. utilitarian robots, using a between-subjects experimental design, whereby 48 college students in Korea were randomly assigned to interact with either a Pleo (Dinosaur robot) or a Roomba (vacuum-cleaning robot). Results revealed that hedonic robot (HR) users perceived more enjoyment than utilitarian robot (UR) users, whereas UR users perceived more usefulness and ease-of-use than HR users. Users with high tendency for parasocial interaction (PSI) and high anthropomorphism had more positive attitudes towards robots than their counterparts with low levels of these traits. HR users with high anthropomorphism and PSI had the most positive attitudes than all other combinations of variables. These results indicate that individual differences play a significant moderating role on user attitudes toward hedonic and utilitarian robots. The results of this study suggest that robot developers and marketers should take seriously the labeling of robots as hedonic or utilitarian, and also consider users' individual differences in order to maximize benefits of human-robot interactions.

In this research, real-time face tracking and gesture recognizing embedded quadruped robot with a tele-operation server is presented. Using i.MX21 embedded system, this robot transfers MPEG-4 video to tele-operation server which processes image data for gesture recognition and face detection, and human following. The developed quadruped robot has 3 DOF 4 legs and pan-tilt actuators. This system can recognize user' s face and hand motion and serve various music contents to robot user.

In this paper, a robust face recognition algorithm is proposed, which is based on the elastic graph matching (EGM) and discriminative feature analysis algorithm. We introduce a cost function for the EGM taking account of variations in face pose and facial expressions, and propose its optimization procedure. Our proposed cost function uses a set of Gabor-wavelet-based features, called robust jet, which are robust against the variations. The robust jet is defined in terms of discrete Fourier transform coefficients of Gabor coefficients. To cope with the difference between face poses of test face and reference faces, 2 x 2 warping matrix is incorporated in the proposed cost function. For the discriminative feature analysis, linear projection discriminant analysis and kernel-based projection discriminant analysis are introduced. These methods are motivated to solve the small-size problem of training samples. The basic idea of PDA is that a class is represented by a subspace spanned by some training samples of the class instead of using sample mean vector, that the distance from a pattern to a class is defined by using the error vector between the pattern and its projection to the subspace representing the class, and that an optimum feature selection rule is developed using the distance concept in a similar way as in the conventional linear discriminant analysis. In order to evaluate the performance of our face recognition algorithm, we carried out some experiments using the well-known FERET face database, and compared the performance with recently developed approaches. We observed that our algorithm outperformed the compared approaches.