U.S. Open follow modal Personalized Content Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens.

TF-CoVR Statistics We present detailed statistics on the distribution of video counts per label in TF-CoVR, which comprises a diverse set of 306 annotated sub-actions. Both distrib video utions distrib are ution plotted for the on a F log ineGym arithmic [3] and scale F to ineDiving emphasize [6] the subsets long-tailed of TF-CoVR nature, of label frequencies. In FineGym, many labels have several hundred to over a thousand associated videos, with a gradual decline across the distribution. By contrast, FineDiving exhibits a steeper drop in video count per label, primarily due to samples, its smaller preserving dataset enough size. Ne div v ersity ertheless, to support a substantial temporal number fine-gr of ained labels composed still contain video more retrieval. A logarithmic scale is used on the y-axis to highlight the steep drop in video counts per label due to the smaller dataset size.

Modern foundation models are trained on diverse datasets to enhance generalization across tasks and domains. A central challenge in this process is determining how to effectively mix and sample data from multiple sources. This naturally leads to a multi-task learning (MTL) perspective. While prior work in MTL has emphasized mitigating gradient conflicts, we observe that large-scale pretraining scenarios--such as multilingual or multi-domain training--often exhibit little to no gradient conflict. Motivated by this observation, we propose PiKE (Positive gradient interaction-based K-task weights Estimator), an adaptive data mixing algorithm that dynamically adjusts sampling weights during training. PiKE exploits non-conflicting gradient interactions to minimize a near-tight upper bound on the average loss decrease at each step, while incurring negligible computational overhead. We provide theoretical convergence guarantees and show that PiKE outperforms static and non-adaptive mixing baselines. Furthermore, we extend PiKE to promote balanced learning across tasks. Extensive experiments on largescale language model pretraining confirm that PiKE achieves faster convergence and improved downstream performance compared to existing approaches.

Modern foundation models are trained on diverse datasets to enhance generalization across tasks and domains. A central challenge in this process is determining how to effectively mix and sample data from multiple sources. This naturally leads to a multi-task learning (MTL) perspective. While prior work in MTL has emphasized mitigating gradient conflicts, we observe that large-scale pretraining scenarios--such as multilingual or multi-domain training--often exhibit little to no gradient conflict. Motivated by this observation, we propose $\textbf{PiKE}$ ($\textbf{P}$ositive gradient $\textbf{i}$nteraction-based $\textbf{K}$-task weights $\textbf{E}$stimator), an adaptive data mixing algorithm that dynamically adjusts sampling weights during training. PiKE exploits non-conflicting gradient interactions to minimize a near-tight upper bound on the average loss decrease at each step, while incurring negligible computational overhead. We provide theoretical convergence guarantees and show that PiKE outperforms static and non-adaptive mixing baselines. Furthermore, we extend PiKE to promote balanced learning across tasks. Extensive experiments on large-scale language model pretraining confirm that PiKE achieves faster convergence and improved downstream performance compared to existing approaches.

Deep learning has become a cornerstone of modern machine learning. It relies heavily on vast datasets and significant computational resources for high performance. This data often contains sensitive information, making privacy a major concern in deep learning. Spiking Neural Networks (SNNs) have emerged as an energy-efficient alternative to conventional deep learning approaches. Nevertheless, SNNs still depend on large volumes of data, inheriting all the privacy challenges of deep learning. Homomorphic encryption addresses this challenge by allowing computations to be performed on encrypted data, ensuring data confidentiality throughout the entire processing pipeline. In this paper, we introduce PRIVSPIKE, a privacy-preserving inference framework for SNNs using the CKKS homomorphic encryption scheme. PRIVSPIKE supports arbitrary depth SNNs and introduces two key algorithms for evaluating the Leaky Integrate-and-Fire activation function: (1) a polynomial approximation algorithm designed for high-performance SNN inference, and (2) a novel scheme-switching algorithm that optimizes precision at a higher computational cost. We evaluate PRIVSPIKE on MNIST, CIFAR-10, Neuromorphic MNIST, and CIFAR-10 DVS using models from LeNet-5 and ResNet-19 architectures, achieving encrypted inference accuracies of 98.10%, 79.3%, 98.1%, and 66.0%, respectively. On a consumer-grade CPU, SNN LeNet-5 models achieved inference times of 28 seconds on MNIST and 212 seconds on Neuromorphic MNIST. For SNN ResNet-19 models, inference took 784 seconds on CIFAR-10 and 1846 seconds on CIFAR-10 DVS. These results establish PRIVSPIKE as a viable and efficient solution for secure SNN inference, bridging the gap between energy-efficient deep neural networks and strong cryptographic privacy guarantees while outperforming prior encrypted SNN solutions.

Modern machine learning models are trained on diverse datasets and tasks to improve generalization. A key challenge in multitask learning is determining the optimal data mixing and sampling strategy across different data sources. Prior research in this multi-task learning setting has primarily focused on mitigating gradient conflicts between tasks. However, we observe that many real-world multitask learning scenarios--such as multilingual training and multi-domain learning in large foundation models--exhibit predominantly positive task interactions with minimal or no gradient conflict. Building on this insight, we introduce PiKE (Positive gradient interaction-based K-task weights Estimator), an adaptive data mixing algorithm that dynamically adjusts task contributions throughout training. PiKE optimizes task sampling to minimize overall loss, effectively leveraging positive gradient interactions with almost no additional computational overhead. We establish theoretical convergence guarantees for PiKE and demonstrate its superiority over static and non-adaptive mixing strategies. Additionally, we extend PiKE to promote fair learning across tasks, ensuring balanced progress and preventing task underrepresentation. Empirical evaluations on large-scale language model pretraining show that PiKE consistently outperforms existing heuristic and static mixing strategies, leading to faster convergence and improved downstream task performance.

Data creation has exploded in the 21st century. There's a camera and recording device in every pocket, which that makes it increasingly difficult for human moderators to stay on top of the explosion in user-generated content - especially when some people purposefully post illegal or harmful images and video. "When we consider that it's been estimated that it would take someone 950 years to check all of the Snaps uploaded to SnapChat every 24 hours, it's obvious that companies cannot moderate this volume of images using human power alone," says Cris Pikes, CEO and co-founder of Image Analyzer. Even massive social media firms like Facebook, which outsource content moderation, struggle to keep up with the growth in harmful, extremist and false content. It has reached the point that the individuals who work in moderation are starting to sue for burn-out, and even post-traumatic stress.

Are four-day workweeks the future? Several businesses have already made the switch, citing improved productivity, happier employees, better retention, and faster hiring. To attain a true four-day (32-hour) workweek, many organizations would have to (A) hire more talent to pick up the slack or (B) accept a less productive year. Neither choice would be useful, but there is a third option coming down the pike: artificial intelligence. AI will be able to improve productivity to the point where working hours can be feasibly reduced for any business, writes Jonathan Crane, Chief Operating Officer at IPsoft.

Storytelling is fundamental to language, including culture, conversation and communication in their broadest senses. It thus emerges as an essential component of intelligent systems, including systems where natural language is not a primary focus or where we do not usually think of a story being involved. In this paper we explore the emergence of storytelling as a requirement in embodied conversational agents, including its role in educational and health interventions, as well as in a general-purpose computer interface for people with disabilities or other constraints that prevent the use of traditional keyboard and speech interfaces. We further present a characterization of storytelling as an inventive fleshing out of detail according to a particular personal perspective, and propose the DREAMT model to focus attention on the different layers that need to be present in a character-driven storytelling system. Most if not all aspects of the DREAMT model have arisen from or been explored in some aspect of our implemented research systems, but currently only at a primitive and relatively unintegrated level. However, this experience leads us to formalize and elaborate the DREAMT model mnemonically as follows: - Description/Dialogue/Definition/Denotation - Realization/Representation/Role - Explanation/Education/Entertainment - Actualization/Activation - Motivation/Modelling - Topicalization/Transformation

The American space agency's InSight lander appears to have detected its first seismic event on Mars. The faint rumble was picked up by the probe's sensors on 6 April - the 128th Martian day, or sol, of the mission. It is the first seismic signal detected on the surface of a planetary body other than the Earth and its Moon. Scientists say the source for this "Marsquake" could either be movement in a crack inside the planet or the shaking from a meteorite impact. Nasa's InSight probe touched down on the Red Planet in November last year. It aims to identify multiple quakes, to help build a clearer picture of Mars' interior structure.