Existing benchmarks that measure cultural adaptation in LLMs are misaligned with the actual challenges these models face when interacting with users from diverse cultural backgrounds. In this work, we introduce the first framework and benchmark designed to evaluate LLMs in realistic, multicultural conversational settings. Grounded in sociocultural theory, our framework formalizes how linguistic style - a key element of cultural communication - is shaped by situational, relational, and cultural context. We construct a benchmark dataset based on this framework, annotated by culturally diverse raters, and propose a new set of desiderata for cross-cultural evaluation in NLP: conversational framing, stylistic sensitivity, and subjective correctness. We evaluate today's top LLMs on our benchmark and show that these models struggle with cultural adaptation in a conversational setting.

The rise of End-Edge-Cloud Collaboration (EECC) offers a promising paradigm for Artificial Intelligence (AI) model training across end devices, edge servers, and cloud data centers, providing enhanced reliability and reduced latency. Hierarchical Federated Learning (HFL) can benefit from this paradigm by enabling multi-tier model aggregation across distributed computing nodes. However, the potential of HFL is significantly constrained by the inherent heterogeneity and dynamic characteristics of EECC environments. Specifically, the uniform model structure bounded by the least powerful end device across all computing nodes imposes a performance bottleneck. Meanwhile, coupled heterogeneity in data distributions and resource capabilities across tiers disrupts hierarchical knowledge transfer, leading to biased updates and degraded performance. Furthermore, the mobility and fluctuating connectivity of computing nodes in EECC environments introduce complexities in dynamic node migration, further compromising the robustness of the training process. To address multiple challenges within a unified framework, we propose End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration (FedEEC), which is a novel EECC-empowered FL framework that allows the trained models from end, edge, to cloud to grow larger in size and stronger in generalization ability. FedEEC introduces two key innovations: (1) Bridge Sample Based Online Distillation Protocol (BSBODP), which enables knowledge transfer between neighboring nodes through generated bridge samples, and (2) Self-Knowledge Rectification (SKR), which refines the transferred knowledge to prevent suboptimal cloud model optimization. The proposed framework effectively handles both cross-tier resource heterogeneity and effective knowledge transfer between neighboring nodes, while satisfying the migration-resilient requirements of EECC.

Federated Learning (FL) enables training Artificial Intelligence (AI) models over end devices without compromising their privacy. As computing tasks are increasingly performed by a combination of cloud, edge, and end devices, FL can benefit from this End-Edge-Cloud Collaboration (EECC) paradigm to achieve collaborative device-scale expansion with real-time access. Although Hierarchical Federated Learning (HFL) supports multi-tier model aggregation suitable for EECC, prior works assume the same model structure on all computing nodes, constraining the model scale by the weakest end devices. To address this issue, we propose Agglomerative Federated Learning (FedAgg), which is a novel EECC-empowered FL framework that allows the trained models from end, edge, to cloud to grow larger in size and stronger in generalization ability. FedAgg recursively organizes computing nodes among all tiers based on Bridge Sample Based Online Distillation Protocol (BSBODP), which enables every pair of parent-child computing nodes to mutually transfer and distill knowledge extracted from generated bridge samples. This design enhances the performance by exploiting the potential of larger models, with privacy constraints of FL and flexibility requirements of EECC both satisfied. Experiments under various settings demonstrate that FedAgg outperforms state-of-the-art methods by an average of 4.53\% accuracy gains and remarkable improvements in convergence rate.

Dynamic structural causal models (SCMs) are a powerful framework for reasoning in dynamic systems about direct effects which measure how a change in one variable affects another variable while holding all other variables constant. The causal relations in a dynamic structural causal model can be qualitatively represented with a full-time causal graph. Assuming linearity and causal sufficiency and given the full-time causal graph, the direct causal effect is always identifiable and can be estimated from data by adjusting on any set of variables given by the so-called single-door criterion. However, in many application such a graph is not available for various reasons but nevertheless experts have access to an abstraction of the full-time causal graph which represents causal relations between time series while omitting temporal information. This paper presents a complete identifiability result which characterizes all cases for which the direct effect is graphically identifiable from summary causal graphs and gives two sound finite adjustment sets that can be used to estimate the direct effect whenever it is identifiable.

In 2015, it was the chosen venue for one of the main events in her field the International Conference on Robotics and Automation (ICRA). But she and other women involved in organizing it felt that the city, famed for its strip clubs, was unsuitable. Among the first achievements of the organizing committee which that year was all-female was moving the conference to Seattle in Washington. The committee had even bigger ambitions for the male-skewed meeting. Often, people say there arent any women speaking because there arent any out there, so we thought, Lets show them a tonne of women and that might change things, she says.

Checking various log files from different processes can be a tedious task as these logs contain lots of events, each with a (possibly large) number of attributes. We developed a way to automatically model log files with a dozen attributes and detect outlier traces in the data. For that we extend Dynamic Bayesian Networks to model the normal behavior found in log files. We introduce a new algorithm that is able to learn a model of a log file starting from the data itself. The model is capable of scoring traces even when new values or new combinations of values appear in the log file and has the ability to give a decomposition of the score indicating the root cause for the anomalies.

We investigate the problem of eliciting CP-nets in the well-known model of exact learning with equivalence and membership queries. The goal is to identify a preference ordering with a binary-valued CP-net by guiding the user through a sequence of queries. Each example is a dominance test on some pair of outcomes. In this setting, we show that acyclic CP-nets are not learnable with equivalence queries alone, while they are learnable with the help of membership queries if the supplied examples are restricted to swaps. A similar property holds for tree CP-nets with arbitrary examples. In fact, membership queries allow us to provide attribute-efficient algorithms for which the query complexity is only logarithmic in the number of attributes. Such results highlight the utility of this model for eliciting CP-nets in large multi-attribute domains.