Generating safety-critical scenarios in high-fidelity simulations offers a promising and cost-effective approach for efficient testing of autonomous vehicles. Existing methods typically rely on manipulating a single vehicle's trajectory through sophisticated designed objectives to induce adversarial interactions, often at the cost of realism and scalability. In this work, we propose the Risk-Adjustable Driving Environment (RADE), a simulation framework that generates statistically realistic and risk-adjustable traffic scenes. Built upon a multi-agent diffusion architecture, RADE jointly models the behavior of all agents in the environment and conditions their trajectories on a surrogate risk measure. Unlike traditional adversarial methods, RADE learns risk-conditioned behaviors directly from data, preserving naturalistic multi-agent interactions with controllable risk levels. To ensure physical plausibility, we incorporate a tokenized dynamics check module that efficiently filters generated trajectories using a motion vocabulary. We validate RADE on the real-world rounD dataset, demonstrating that it preserves statistical realism across varying risk levels and naturally increases the likelihood of safety-critical events as the desired risk level grows up. Our results highlight RADE's potential as a scalable and realistic tool for AV safety evaluation.

When a network slice spans multiple domains, each domain must uphold the End-to-End (E2E) Service Level Agreement (SLA) associated with the slice. This requires decomposing the E2E SLA into partial SLAs for each domain. In a two-level network slicing management system with an E2E orchestrator and local controllers, we propose an online learning-decomposition framework that dynamically updates risk models using recent feedback. This approach utilizes online gradient descent and FIFO memory buffers to enhance stability and robustness. Our empirical study shows the proposed framework outperforms state-of-the-art static methods, offering more accurate and resilient SLA decomposition under varying conditions and sparse data.

Evaluating open-domain dialogue systems is challenging for reasons such as the one-to-many problem, i.e., many appropriate responses other than just the golden response. As of now, automatic evaluation methods need better consistency with humans, while reliable human evaluation can be time- and cost-intensive. To this end, we propose the Reference-Assisted Dialogue Evaluation (RADE) approach under the multi-task learning framework, which leverages the pre-created utterance as reference other than the gold response to relief the one-to-many problem. Specifically, RADE explicitly compares reference and the candidate response to predict their overall scores. Moreover, an auxiliary response generation task enhances prediction via a shared encoder. To support RADE, we extend three datasets with additional rated responses other than just a golden response by human annotation. Experiments on our three datasets and two existing benchmarks demonstrate the effectiveness of our method, where Pearson, Spearman, and Kendall correlations with human evaluation outperform state-of-the-art baselines.

If you drive in the United States, chances are you can't remember the last time you bought a paper map, printed out a digital map, or even stopped to ask for directions. Thanks to Global Positioning System (GPS) and the mobile mapping apps on our smartphones and their real-time routing advice, navigation is a solved problem. If you live in a place like Doha, Qatar, where the length of the road network has tripled over the last five years, commercial mapping services from Google, Apple, Bing, or other providers simply can't keep up with the pace of infrastructure change. "Each one of us who grew up in Europe or the US probably cannot understand the scale at which these cities grow," says Rade Stanojevic, a senior scientist at the Qatar Computing Research Institute (QCRI), part of Hamad Bin Khalifa University, a Qatar Foundation university, in Doha. "Pretty much every neighborhood sees a new underpass, new overpass, new large highway being added every couple of months." As Qatar copes with this rapid growth--and especially as it prepares to host the FIFA World Cup in 2022--the bad routing advice and accumulating travel delays from outdated digital maps is increasingly costly. That's why Stanojevic and colleagues at QCRI decided to try applying machine learning to the problem. A road network can be interpreted as a giant graph in which every intersection is a node and every road is an edge, says Stanojevic, whose specialty is network economics. Road segments can have both static characteristics, such as the designated speed limit, and dynamic characteristics, such as rush-hour congestion. To see where traffic really is going--rather than where an old map says it should go--and then predict the best routes through an ever-changing maze, all a machine-learning model would need is lots of up-to-data data on both the static and dynamic factors. "Fortunately enough, modern vehicle fleets have these monitoring systems that produce quite a lot of data," says Stanojevic.

Decision-tree-based ensemble classification methods (DTEMs) are a prevalent tool for supervised anomaly detection. However, due to the continued growth of datasets, DTEMs result in increasing drawbacks such as growing memory footprints, longer training times, and slower classification latencies at lower throughput. In this paper, we present, design, and evaluate RADE - a DTEM-based anomaly detection framework that augments standard DTEM classifiers and alleviates these drawbacks by relying on two observations: (1) we find that a small (coarse-grained) DTEM model is sufficient to classify the majority of the classification queries correctly, such that a classification is valid only if its corresponding confidence level is greater than or equal to a predetermined classification confidence threshold; (2) we find that in these fewer harder cases where our coarse-grained DTEM model results in insufficient confidence in its classification, we can improve it by forwarding the classification query to one of expert DTEM (fine-grained) models, which is explicitly trained for that particular case. We implement RADE in Python based on scikit-learn and evaluate it over different DTEM methods: RF, XGBoost, AdaBoost, GBDT and LightGBM, and over three publicly available datasets. Our evaluation over both a strong AWS EC2 instance and a Raspberry Pi 3 device indicates that RADE offers competitive and often superior anomaly detection capabilities as compared to standard DTEM methods, while significantly improving memory footprint (by up to 5.46x), training-time (by up to 17.2x), and classification latency (by up to 31.2x).