Frequent software updates lead to log evolution, posing generalization challenges for current log anomaly detection. Traditional log anomaly detection research focuses on using small deep learning models (SMs), but these models inherently lack generalization due to their closed-world assumption. Large language models (LLMs) exhibit strong semantic understanding and generalization capabilities, making them promising for log anomaly detection. However, they suffer from computational inefficiencies. To balance efficiency and generalization, we propose a collaborative log anomaly detection scheme (CoorLog) that uses an adaptive coordinator to integrate SM and LLM. The coordinator determines if incoming logs have evolved. Non-evolved logs are routed to the SM, while evolved logs are directed to the LLM for detailed inference using the constructed Evol-CoT. To gradually adapt to evolution, we introduce the adaptive evolution mechanism (AEM), which updates the coordinator to redirect evolved logs identified by the LLM to the SM. Simultaneously, the SM is fine-tuned to inherit the LLM’s judgment on these logs. Extensive experiments on real-world datasets demonstrate that CoorLog achieves superior F1-scores in both intra-version and inter-version anomaly detection. Additionally, CoorLog reduces processing time by 91.63% and token consumption by 85.59% compared to using an LLM alone.

As pretrained text-to-image diffusion models become in-creasingly powerful, recent efforts have been made to distill knowledge from these text-to-image pretrained models for optimizing a text-guided 3D model. Most of the existing methods generate a holistic 3D model from a plain text input. This can be problematic when the text describes a complex scene with multiple objects, because the vectorized text embeddings are inherently unable to capture a complex description with multiple entities and relationships. Holistic 3D modeling of the entire scene further prevents accurate grounding of text entities and concepts. To address this limitation, we propose GraphDreamer, a novel framework to generate compositional 3D scenes from scene graphs, where objects are represented as nodes and their interactions as edges. By exploiting node and edge information in scene graphs, our method makes better use of the pretrained text-to-image diffusion model and is able to fully disentangle different objects without image-level supervision. To facil-itate modeling of object-wise relationships, we use signed distance fields as representation and impose a constraint to avoid inter-penetration of objects. To avoid manual scene graph creation, we design a text prompt for ChatGPT to generate scene graphs based on text inputs. We conduct both qualitative and quantitative experiments to validate the effectiveness of GraphDreamer in generating high-fidelity compositional 3D scenes with disentangled object entities.

Improving the performance of face forgery detectors often requires more identity-swapped images of higher-quality. One core objective of identity swapping is to generate identity-discriminative faces that are distinct from the target while identical to the source. To this end, properly disentangling identity and identity-irrelevant information is critical and remains a challenging endeavor. In this work, we propose a novel information disentangling and swapping network, called InfoSwap, to extract the most expressive information for identity representation from a pre-trained face recognition model. The key insight of our method is to formulate the learning of disentangled representations as optimizing an information bottleneck tradeoff, in terms of finding an optimal compression of the pretrained latent features. Moreover, a novel identity contrastive loss is proposed for further disentanglement by requiring a proper distance between the generated identity and the target. While the most prior works have focused on using various loss functions to implicitly guide the learning of representations, we demonstrate that our model can provide explicit supervision for learning disentangled representations, achieving impressive performance in generating more identity-discriminative swapped faces.

The widespread adoption of home robots shows a high demand for in-home assistance. Since single women account for a large proportion of the Chinese population, it is important to design home robots to support their lives at home. This study aims to explore the possible design features of home robots to support single women in China. Interviews and an online survey were used to gauge user perception and expectations of home robots. Our research reveals the unique lifestyle preferences of single women in China and how home robots could be designed to support their needs. We discuss our findings and design implications based on three aspects: lifestyle, intelligence, and sense, to inspire better robot design for women.

Scientific collaboration is vital to many fields, and it is common to see scholars seek out experienced researchers or experts in a domain with whom they can share knowledge, experience, and resources. To explore the diversity of research collaborations, this article performs a temporal analysis on the scientific careers of researchers in the field of computer science. Specifically, we analyze collaborators using 2 indicators: the research topic diversity, measured by the Author‐Conference‐Topic model and cosine, and the impact diversity, measured by the normalized standard deviation of h‐indices. We find that the collaborators of high‐impact researchers tend to study diverse research topics and have diverse h‐indices. Moreover, by setting PhD graduation as an important milestone in researchers' careers, we examine several indicators related to scientific collaboration and their effects on a career. The results show that collaborating with authoritative authors plays an important role prior to a researcher's PhD graduation, but working with non‐authoritative authors carries more weight after PhD graduation.