Real-world applications often face scarce labeled data due to the high cost and time requirements of gold-standard experiments, whereas unlabeled data are typically abundant. With the growing adoption of machine learning techniques, it has become increasingly feasible to generate multiple predicted labels using a variety of models and algorithms, including deep learning, large language models, and generative AI. In this paper, we propose a novel approach that safely and adaptively aggregates multiple black-box predictions with unknown quality while preserving valid statistical inference. Our method provides two key guarantees: (i) it never performs worse than using the labeled data alone, regardless of the quality of the predictions; and (ii) if any one of the predictions (without knowing which one) perfectly fits the ground truth, the algorithm adaptively exploits this to achieve either a faster convergence rate or the semiparametric efficiency bound. We demonstrate the effectiveness of the proposed algorithm through experiments on both synthetic and benchmark datasets.

We explore the performance of several state-of-the-art automatic speech recognition (ASR) models on a large-scale Arabic speech dataset, the SADA (Saudi Audio Dataset for Arabic), which contains 668 hours of high-quality audio from Saudi television shows. The dataset includes multiple dialects and environments, specifically a noisy subset that makes it particularly challenging for ASR. We evaluate the performance of the models on the SADA test set, and we explore the impact of fine-tuning, language models, as well as noise and denoising on their performance. We find that the best performing model is the MMS 1B model finetuned on SADA with a 4-gram language model that achieves a WER of 40.9\% and a CER of 17.6\% on the SADA test clean set.

Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce per-step computation cost, while effectively reducing sampling time, demonstrate low faithfulness compared to the original baseline. We hypothesize that this fidelity gap arises because (a) different prompts correspond to varying denoising trajectory, and (b) such methods do not consider the underlying ODE formulation and its numerical solution. In this paper, we propose Stability-guided Adaptive Diffusion Acceleration (SADA), a novel paradigm that unifies step-wise and token-wise sparsity decisions via a single stability criterion to accelerate sampling of ODE-based generative models (Diffusion and Flow-matching). For (a), SADA adaptively allocates sparsity based on the sampling trajectory. For (b), SADA introduces principled approximation schemes that leverage the precise gradient information from the numerical ODE solver. Comprehensive evaluations on SD-2, SDXL, and Flux using both EDM and DPM++ solvers reveal consistent $\ge 1.8\times$ speedups with minimal fidelity degradation (LPIPS $\leq 0.10$ and FID $\leq 4.5$) compared to unmodified baselines, significantly outperforming prior methods. Moreover, SADA adapts seamlessly to other pipelines and modalities: It accelerates ControlNet without any modifications and speeds up MusicLDM by $1.8\times$ with $\sim 0.01$ spectrogram LPIPS.

Q-learning algorithms are appealing for real-world applications due to their data-efficiency, but they are very prone to overfitting and training instabilities when trained from visual observations. Prior work, namely SVEA, finds that selective application of data augmentation can improve the visual generalization of RL agents without destabilizing training. We revisit its recipe for data augmentation, and find an assumption that limits its effectiveness to augmentations of a photometric nature. Addressing these limitations, we propose a generalized recipe, SADA, that works with wider varieties of augmentations. We benchmark its effectiveness on DMC-GB2 - our proposed extension of the popular DMControl Generalization Benchmark - as well as tasks from Meta-World and the Distracting Control Suite, and find that our method, SADA, greatly improves training stability and generalization of RL agents across a diverse set of augmentations. For visualizations, code and benchmark: see https://aalmuzairee.github.io/SADA/

In today's globalized world, bridging the cultural divide is more critical than ever for forging meaningful connections. The Socially-Aware Dialogue Assistant System (SADAS) is our answer to this global challenge, and it's designed to ensure that conversations between individuals from diverse cultural backgrounds unfold with respect and understanding. Our system's novel architecture includes: (1) identifying the categories of norms present in the dialogue, (2) detecting potential norm violations, (3) evaluating the severity of these violations, (4) implementing targeted remedies to rectify the breaches, and (5) articulates the rationale behind these corrective actions. We employ a series of State-Of-The-Art (SOTA) techniques to build different modules, and conduct numerous experiments to select the most suitable backbone model for each of the modules. We also design a human preference experiment to validate the overall performance of the system. We will open-source our system (including source code, tools and applications), hoping to advance future research. A demo video of our system can be found at:~\url{https://youtu.be/JqetWkfsejk}. We have released our code and software at:~\url{https://github.com/AnonymousEACLDemo/SADAS}.

In the past year or so, since the public release of OpenAI's ChatGPT, people have been making their peace with the idea that an omnipotent AI might be on the horizon. Sam Altman, the company's CEO, "believes that people need time to reckon with the idea that we may soon share Earth with a powerful new intelligence, before it remakes everything from work to human relationships," my colleague Ross Andersen reported after the two had several conversations. "ChatGPT was a way of serving notice." But OpenAI isn't Altman's only project, and it's not even his only project with ambitions to change the world. He is also a co-founder of a company called Tools for Humanity, which has the lofty goal of protecting people from the economic devastation that may arise from AI taking human jobs. The company's first major project is Worldcoin, which uses an evil-looking metallic orb--called the Orb--to take eyeball scans from people all over the world.

Domain generalization (DG) aims to train a model to perform well in unseen domains under different distributions. This paper considers a more realistic yet more challenging scenario,namely Single Domain Generalization (Single-DG), where only a single source domain is available for training. To tackle this challenge, we first try to understand when neural networks fail to generalize? We empirically ascertain a property of a model that correlates strongly with its generalization that we coin as "model sensitivity". Based on our analysis, we propose a novel strategy of Spectral Adversarial Data Augmentation (SADA) to generate augmented images targeted at the highly sensitive frequencies. Models trained with these hard-to-learn samples can effectively suppress the sensitivity in the frequency space, which leads to improved generalization performance. Extensive experiments on multiple public datasets demonstrate the superiority of our approach, which surpasses the state-of-the-art single-DG methods.

Global technology consultancy SADA has closed a five-year, $50 million deal with ad tech provider MadHive to expand the over-the-top (OTT) ad solutions company's use of Google Cloud technologies to deliver new products and services. MadHive's end-to-end advertising solution -- based on cryptography, blockchain and AI to power modern media -- was first deployed on the Google Cloud Platform (Google Cloud) in 2017 with help from Google Cloud Premier Partner SADA. The challenge was to deliver MadHive's next-generation platform at scale with low latency while supporting a rapid, iterative development cycle, machine learning requirements, and a short go-to-market timeline. "SADA's first step with Madhive was analysing the limits of the Kubernetes- and Docker-based implementation they had previously used for prototypes," said SADA director of cloud adoption Simon Margolis. MadHive said that from ideation to research, patent and deployment, Google Cloud's big data and machine learning tools were the only backend technologies capable of meeting its technical demands.

The Internet of Things (IoT) and Artificial Intelligence (AI) duked it out in SADA Systems survey on trends expected to take over the tech industry this year. SADA, a global tech and business consulting firm, found that 67% of respondents said IoT technology was currently being developed or used by their company or institution. Of the 500 IT specialists and 100 executives that SADA spoke with for the survey, 60% said AI was also taking a prominent role in their operations and was something they were looking to invest in more. AI just barely beat out IoT as the technology companies were investing the most amount of money in over the next two years, with blockchain coming in at a distant second. AI dominated much of the survey, with respondents saying the technology would have an outsized impact on business entities as well as society as a whole.

The Internet of Things (IoT) and Artificial Intelligence (AI) duked it out in SADA Systems survey on trends expected to take over the tech industry this year. SADA, a global tech and business consulting firm, found that 67% of respondents said IoT technology was currently being developed or used by their company or institution. Of the 500 IT specialists and 100 executives that SADA spoke with for the survey, 60% said AI was also taking a prominent role in their operations and was something they were looking to invest in more. AI just barely beat out IoT as the technology companies were investing the most amount of money in over the next two years, with blockchain coming in at a distant second. AI dominated much of the survey, with respondents saying the technology would have an outsized impact on business entities as well as society as a whole.