In this paper, we introduce the Generalized Auto Segmentation (GAS), an end-to-end, cross-domain personalization platform developed at Meta. GAS is designed to optimize personalization policies for online experiments, operating independently of any specific server infrastructure. Our process begins with a seed experiment to collect user data, which is followed by feature logging and selection. User segmentation is then performed using a feature-threshold method. Specifically, we utilize simple combinations of single or dual features to identify concise, explainable, and sustainable user cohorts that enhance both business outcomes and user experience over the long term. Treatments and the reward function for these segments are refined through ParallAX, a novel methodology at Meta that uses offline estimates to optimize online metrics, ensuring impactful and precisely tailored interventions for diverse user groups. The deployment of GAS across various Meta productions has demonstrated its efficiency and effectiveness.

With the emergence of transformer-based architectures and large language models (LLMs), the accuracy of road scene perception has substantially advanced. Nonetheless, current road scene segmentation approaches are predominantly trained on closed-set data, resulting in insufficient detection capabilities for out-of-distribution (OOD) objects. To overcome this limitation, road anomaly detection methods have been proposed. However, existing methods primarily depend on image inpainting and OOD distribution detection techniques, facing two critical issues: (1) inadequate consideration of the objectiveness attributes of anomalous regions, causing incomplete segmentation when anomalous objects share similarities with known classes, and (2) insufficient attention to environmental constraints, leading to the detection of anomalies irrelevant to autonomous driving tasks. In this paper, we propose a novel framework termed Segmenting Objectiveness and Task-Awareness (SOTA) for autonomous driving scenes. Specifically, SOTA enhances the segmentation of objectiveness through a Semantic Fusion Block (SFB) and filters anomalies irrelevant to road navigation tasks using a Scene-understanding Guided Prompt-Context Adaptor (SG-PCA). Extensive empirical evaluations on multiple benchmark datasets, including Fishyscapes Lost and Found, Segment-Me-If-You-Can, and RoadAnomaly, demonstrate that the proposed SOTA consistently improves OOD detection performance across diverse detectors, achieving robust and accurate segmentation outcomes.

In the past decade, the technology industry has adopted online controlled experiments (a.k.a. A/B testing) to guide business decisions. In practice, A/B tests are often implemented with increasing treatment allocation: the new treatment is gradually released to an increasing number of units through a sequence of randomized experiments. In scenarios such as experimenting in a social network setting or in a bipartite online marketplace, interference among units may exist, which can harm the validity of simple inference procedures. In this work, we introduce a widely applicable procedure to test for interference in A/B testing with increasing allocation. Our procedure can be implemented on top of an existing A/B testing platform with a separate flow and does not require a priori a specific interference mechanism. In particular, we introduce two permutation tests that are valid under different assumptions. Firstly, we introduce a general statistical test for interference requiring no additional assumption. Secondly, we introduce a testing procedure that is valid under a time fixed effect assumption. The testing procedure is of very low computational complexity, it is powerful, and it formalizes a heuristic algorithm implemented already in industry. We demonstrate the performance of the proposed testing procedure through simulations on synthetic data. Finally, we discuss one application at LinkedIn, where a screening step is implemented to detect potential interference in all their marketplace experiments with the proposed methods in the paper.

As the global economy's demand for computer applications soars, the demand for well-trained computer science (CS) professionals is rising. This trend fuels a surge in CS undergraduate degree production which, in turn, puts a strain on departmental resources. In addition, CS departments have to contend with high dropout and failure rates, fragile learning and bimodal outcomes \citeRobins19. Thus, the need for effective teaching techniques in CS education is greater than ever. Some concepts and skills in CS are very difficult to acquire such as analyzing the running time of short pieces of code \citeAlbluwi21, and particularly, computing the running time of loops. Most instructors use a trace-sum-approximate flow chart described in \citeAlbluwi21 to teach students how to analyze the running time of code. The two most important skills in this analysis process are the tracing of code and the approximation of the sum of different number patterns, e.g. the sum of the linear number pattern 1+2+3+...+n is equal to \fracn*(n+1) 2 and it is approximated to O(n^2). Novice programmers struggle with both these integral skills \citeCunningham17, Farghally17. Visual systems have been recognized to improve students' understanding of these concepts \citeFarghally17. Several tools have been developed to assist students with running time analysis. Existing tools are targeted at students with more advanced training, such as a background in advanced data structures (AAV \citeFarghally17 ) or experience with code tracing and approximation of the sum of different number patterns (Compigorithm \citeSmith20 ). However, none of the existing tools teach students how to compute the running time at the introductory level, and this gap presented a unique opportunity for us. An effective run-time analysis visualization system for introductory courses must depict the tracing and approximation of the sum. We propose a design in which the depiction of the loop tracing for run-time analysis is done through the use of a table, where the columns represent loop variables and each row represents one iteration of the loop. More specifically, it tabulates the operations in the order they happen during the execution of the loop as shown in Figure~\reffig:ravic. The table is displayed alongside the program. The current line of code being executed is highlighted while the table information is updated. At the end of the execution, the number of operations is determined by summing all the operations in the table column-by-column from the right-most side to the left as shown in Figure~\reffig:ravic. The student controls the visualization using navigation arrows to go back and forth. Instructors use a similar technique in the tracing of loops, but this approach allows students to proceed at their own pace. The tool is currently being developed as an extension to VS Code.

The fast development of object detection techniques has attracted attention to developing efficient Deep Neural Networks (DNNs). However, the current state-of-the-art DNN models can not provide a balanced solution among accuracy, speed, and model size. This paper proposes an efficient real-time object detection framework on resource-constricted hardware devices through hardware and software co-design. The Tensor Train (TT) decomposition is proposed for compressing the YOLOv5 model. By unitizing the unique characteristics given by the TT decomposition, we develop an efficient hardware accelerator based on FPGA devices. Experimental results show that the proposed method can significantly reduce the model size and improve the execution time.

Nowadays, from companies to academics, researchers across the world are interested in developing recurrent neural networks due to their incredible feats in various applications, such as speech recognition, video detection, predictions, and machine translation. However, the advantages of recurrent neural networks accompanied by high computational and power demands, which are a major design constraint for electronic devices with limited resources used in such network implementations. Optimizing the recurrent neural networks, such as model compression, is crucial to ensure the broad deployment of recurrent neural networks and promote recurrent neural networks for implementing most resource-constrained scenarios. Among many techniques, tensor train (TT) decomposition is considered an up-and-coming technology. Although our previous efforts have achieved 1) expanding limits of many multiplications within eliminating all redundant computations; and 2) decomposing into multi-stage processing to reduce memory traffic, this work still faces some limitations. In particular, current TT decomposition on recurrent neural networks leads to a complex computation sensitive to the quality of training datasets. In this paper, we investigate a new method for TT decomposition on recurrent neural networks for constructing an efficient model within imbalance datasets to overcome this issue. Experimental results show that the proposed new training method can achieve significant improvements in accuracy, precision, recall, F1-score, False Negative Rate (FNR), and False Omission Rate (FOR).