NVIDIA and South Korea align on sovereign AI at APEC CEO SummitAI News At the APEC CEO Summit, NVIDIA said it is working with public agencies and private companies to build sovereign AI infrastructure across South Korea. The plan includes hundreds of thousands of NVIDIA GPUs across sovereign clouds and AI factories for areas like automotive, manufacturing and telecommunications. “Korea’s leadership in technology and manufacturing positions it at
The post NVIDIA and South Korea align on sovereign AI at APEC CEO Summit appeared first on AI News.
At the APEC CEO Summit, NVIDIA said it is working with public agencies and private companies to build sovereign AI infrastructure across South Korea. The plan includes hundreds of thousands of NVIDIA GPUs across sovereign clouds and AI factories for areas like automotive, manufacturing and telecommunications. “Korea’s leadership in technology and manufacturing positions it at
The post NVIDIA and South Korea align on sovereign AI at APEC CEO Summit appeared first on AI News. Read More
DevOps for AI: Continuous deployment pipelines for machine learning systemsAI News AI’s effects on continuous development and deployment pipelines are becoming difficult to ignore. However, decision-makers in software development functions need to consider a broad range of elements when considering the uses of the technology. The challenges of deploying AI at scale Deploying artificial intelligence isn’t the same as deploying, for example, a web app. Traditional
The post DevOps for AI: Continuous deployment pipelines for machine learning systems appeared first on AI News.
AI’s effects on continuous development and deployment pipelines are becoming difficult to ignore. However, decision-makers in software development functions need to consider a broad range of elements when considering the uses of the technology. The challenges of deploying AI at scale Deploying artificial intelligence isn’t the same as deploying, for example, a web app. Traditional
The post DevOps for AI: Continuous deployment pipelines for machine learning systems appeared first on AI News. Read More
From ambition to accountability: Quantifying AI ROI in strategyAI News For many UK executives, AI investment has become a necessity, not an experiment in innovation. Boards now demand evidence of measurable impact – whether through efficiency gains, revenue growth, or reduced operational risk. Yet, as Pete Smyth, CEO of Leading Resolutions notes, many SMEs treat AI as an exploratory exercise, not a structured business strategy.
The post From ambition to accountability: Quantifying AI ROI in strategy appeared first on AI News.
For many UK executives, AI investment has become a necessity, not an experiment in innovation. Boards now demand evidence of measurable impact – whether through efficiency gains, revenue growth, or reduced operational risk. Yet, as Pete Smyth, CEO of Leading Resolutions notes, many SMEs treat AI as an exploratory exercise, not a structured business strategy.
The post From ambition to accountability: Quantifying AI ROI in strategy appeared first on AI News. Read More
Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustnesscs.AI updates on arXiv.org arXiv:2510.27213v1 Announce Type: cross
Abstract: We propose a novel continual self-supervised learning (CSSL) framework for simultaneously learning diverse features from multi-window-obtained chest computed tomography (CT) images and ensuring data privacy. Achieving a robust and highly generalizable model in medical image diagnosis is challenging, mainly because of issues, such as the scarcity of large-scale, accurately annotated datasets and domain shifts inherent to dynamic healthcare environments. Specifically, in chest CT, these domain shifts often arise from differences in window settings, which are optimized for distinct clinical purposes. Previous CSSL frameworks often mitigated domain shift by reusing past data, a typically impractical approach owing to privacy constraints. Our approach addresses these challenges by effectively capturing the relationship between previously learned knowledge and new information across different training stages through continual pretraining on unlabeled images. Specifically, by incorporating a latent replay-based mechanism into CSSL, our method mitigates catastrophic forgetting due to domain shifts during continual pretraining while ensuring data privacy. Additionally, we introduce a feature distillation technique that integrates Wasserstein distance-based knowledge distillation (WKD) and batch-knowledge ensemble (BKE), enhancing the ability of the model to learn meaningful, domain-shift-robust representations. Finally, we validate our approach using chest CT images obtained across two different window settings, demonstrating superior performance compared with other approaches.
arXiv:2510.27213v1 Announce Type: cross
Abstract: We propose a novel continual self-supervised learning (CSSL) framework for simultaneously learning diverse features from multi-window-obtained chest computed tomography (CT) images and ensuring data privacy. Achieving a robust and highly generalizable model in medical image diagnosis is challenging, mainly because of issues, such as the scarcity of large-scale, accurately annotated datasets and domain shifts inherent to dynamic healthcare environments. Specifically, in chest CT, these domain shifts often arise from differences in window settings, which are optimized for distinct clinical purposes. Previous CSSL frameworks often mitigated domain shift by reusing past data, a typically impractical approach owing to privacy constraints. Our approach addresses these challenges by effectively capturing the relationship between previously learned knowledge and new information across different training stages through continual pretraining on unlabeled images. Specifically, by incorporating a latent replay-based mechanism into CSSL, our method mitigates catastrophic forgetting due to domain shifts during continual pretraining while ensuring data privacy. Additionally, we introduce a feature distillation technique that integrates Wasserstein distance-based knowledge distillation (WKD) and batch-knowledge ensemble (BKE), enhancing the ability of the model to learn meaningful, domain-shift-robust representations. Finally, we validate our approach using chest CT images obtained across two different window settings, demonstrating superior performance compared with other approaches. Read More
Higher-order Linear Attentioncs.AI updates on arXiv.org arXiv:2510.27258v1 Announce Type: cross
Abstract: The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically restricted to first-order or kernel-based approximations, which can limit expressivity. We introduce Higher-order Linear Attention (HLA), a causal, streaming mechanism that realizes higher interactions via compact prefix sufficient statistics. In the second-order case, HLA maintains a constant-size state and computes per-token outputs in linear time without materializing any $n times n$ matrices. We give closed-form streaming identities, a strictly causal masked variant using two additional summaries, and a chunk-parallel training scheme based on associative scans that reproduces the activations of a serial recurrence exactly. We further outline extensions to third and higher orders. Collectively, these results position HLA as a principled, scalable building block that combines attention-like, data-dependent mixing with the efficiency of modern recurrent architectures. Project Page: https://github.com/yifanzhang-pro/HLA.
arXiv:2510.27258v1 Announce Type: cross
Abstract: The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically restricted to first-order or kernel-based approximations, which can limit expressivity. We introduce Higher-order Linear Attention (HLA), a causal, streaming mechanism that realizes higher interactions via compact prefix sufficient statistics. In the second-order case, HLA maintains a constant-size state and computes per-token outputs in linear time without materializing any $n times n$ matrices. We give closed-form streaming identities, a strictly causal masked variant using two additional summaries, and a chunk-parallel training scheme based on associative scans that reproduces the activations of a serial recurrence exactly. We further outline extensions to third and higher orders. Collectively, these results position HLA as a principled, scalable building block that combines attention-like, data-dependent mixing with the efficiency of modern recurrent architectures. Project Page: https://github.com/yifanzhang-pro/HLA. Read More
Generative Semantic Coding for Ultra-Low Bitrate Visual Communication and Analysiscs.AI updates on arXiv.org arXiv:2510.27324v1 Announce Type: cross
Abstract: We consider the problem of ultra-low bit rate visual communication for remote vision analysis, human interactions and control in challenging scenarios with very low communication bandwidth, such as deep space exploration, battlefield intelligence, and robot navigation in complex environments. In this paper, we ask the following important question: can we accurately reconstruct the visual scene using only a very small portion of the bit rate in existing coding methods while not sacrificing the accuracy of vision analysis and performance of human interactions? Existing text-to-image generation models offer a new approach for ultra-low bitrate image description. However, they can only achieve a semantic-level approximation of the visual scene, which is far insufficient for the purpose of visual communication and remote vision analysis and human interactions. To address this important issue, we propose to seamlessly integrate image generation with deep image compression, using joint text and coding latent to guide the rectified flow models for precise generation of the visual scene. The semantic text description and coding latent are both encoded and transmitted to the decoder at a very small bit rate. Experimental results demonstrate that our method can achieve the same image reconstruction quality and vision analysis accuracy as existing methods while using much less bandwidth. The code will be released upon paper acceptance.
arXiv:2510.27324v1 Announce Type: cross
Abstract: We consider the problem of ultra-low bit rate visual communication for remote vision analysis, human interactions and control in challenging scenarios with very low communication bandwidth, such as deep space exploration, battlefield intelligence, and robot navigation in complex environments. In this paper, we ask the following important question: can we accurately reconstruct the visual scene using only a very small portion of the bit rate in existing coding methods while not sacrificing the accuracy of vision analysis and performance of human interactions? Existing text-to-image generation models offer a new approach for ultra-low bitrate image description. However, they can only achieve a semantic-level approximation of the visual scene, which is far insufficient for the purpose of visual communication and remote vision analysis and human interactions. To address this important issue, we propose to seamlessly integrate image generation with deep image compression, using joint text and coding latent to guide the rectified flow models for precise generation of the visual scene. The semantic text description and coding latent are both encoded and transmitted to the decoder at a very small bit rate. Experimental results demonstrate that our method can achieve the same image reconstruction quality and vision analysis accuracy as existing methods while using much less bandwidth. The code will be released upon paper acceptance. Read More
LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEvalcs.AI updates on arXiv.org arXiv:2510.26995v1 Announce Type: cross
Abstract: Large language models (LLMs) excel at numerical estimation but struggle to correctly quantify uncertainty. We study how well LLMs construct confidence intervals around their own answers and find that they are systematically overconfident. To evaluate this behavior, we introduce FermiEval, a benchmark of Fermi-style estimation questions with a rigorous scoring rule for confidence interval coverage and sharpness. Across several modern models, nominal 99% intervals cover the true answer only 65% of the time on average. With a conformal prediction based approach that adjusts the intervals, we obtain accurate 99% observed coverage, and the Winkler interval score decreases by 54%. We also propose direct log-probability elicitation and quantile adjustment methods, which further reduce overconfidence at high confidence levels. Finally, we develop a perception-tunnel theory explaining why LLMs exhibit overconfidence: when reasoning under uncertainty, they act as if sampling from a truncated region of their inferred distribution, neglecting its tails.
arXiv:2510.26995v1 Announce Type: cross
Abstract: Large language models (LLMs) excel at numerical estimation but struggle to correctly quantify uncertainty. We study how well LLMs construct confidence intervals around their own answers and find that they are systematically overconfident. To evaluate this behavior, we introduce FermiEval, a benchmark of Fermi-style estimation questions with a rigorous scoring rule for confidence interval coverage and sharpness. Across several modern models, nominal 99% intervals cover the true answer only 65% of the time on average. With a conformal prediction based approach that adjusts the intervals, we obtain accurate 99% observed coverage, and the Winkler interval score decreases by 54%. We also propose direct log-probability elicitation and quantile adjustment methods, which further reduce overconfidence at high confidence levels. Finally, we develop a perception-tunnel theory explaining why LLMs exhibit overconfidence: when reasoning under uncertainty, they act as if sampling from a truncated region of their inferred distribution, neglecting its tails. Read More
How to Design a Persistent Memory and Personalized Agentic AI System with Decay and Self-Evaluation?MarkTechPost In this tutorial, we explore how to build an intelligent agent that remembers, learns, and adapts to us over time. We implement a Persistent Memory & Personalisation system using simple, rule-based logic to simulate how modern Agentic AI frameworks store and recall contextual information. As we progress, we see how the agent’s responses evolve with
The post How to Design a Persistent Memory and Personalized Agentic AI System with Decay and Self-Evaluation? appeared first on MarkTechPost.
In this tutorial, we explore how to build an intelligent agent that remembers, learns, and adapts to us over time. We implement a Persistent Memory & Personalisation system using simple, rule-based logic to simulate how modern Agentic AI frameworks store and recall contextual information. As we progress, we see how the agent’s responses evolve with
The post How to Design a Persistent Memory and Personalized Agentic AI System with Decay and Self-Evaluation? appeared first on MarkTechPost. Read More
Learning Soft Robotic Dynamics with Active Explorationcs.AI updates on arXiv.org arXiv:2510.27428v1 Announce Type: cross
Abstract: Soft robots offer unmatched adaptability and safety in unstructured environments, yet their compliant, high-dimensional, and nonlinear dynamics make modeling for control notoriously difficult. Existing data-driven approaches often fail to generalize, constrained by narrowly focused task demonstrations or inefficient random exploration. We introduce SoftAE, an uncertainty-aware active exploration framework that autonomously learns task-agnostic and generalizable dynamics models of soft robotic systems. SoftAE employs probabilistic ensemble models to estimate epistemic uncertainty and actively guides exploration toward underrepresented regions of the state-action space, achieving efficient coverage of diverse behaviors without task-specific supervision. We evaluate SoftAE on three simulated soft robotic platforms — a continuum arm, an articulated fish in fluid, and a musculoskeletal leg with hybrid actuation — and on a pneumatically actuated continuum soft arm in the real world. Compared with random exploration and task-specific model-based reinforcement learning, SoftAE produces more accurate dynamics models, enables superior zero-shot control on unseen tasks, and maintains robustness under sensing noise, actuation delays, and nonlinear material effects. These results demonstrate that uncertainty-driven active exploration can yield scalable, reusable dynamics models across diverse soft robotic morphologies, representing a step toward more autonomous, adaptable, and data-efficient control in compliant robots.
arXiv:2510.27428v1 Announce Type: cross
Abstract: Soft robots offer unmatched adaptability and safety in unstructured environments, yet their compliant, high-dimensional, and nonlinear dynamics make modeling for control notoriously difficult. Existing data-driven approaches often fail to generalize, constrained by narrowly focused task demonstrations or inefficient random exploration. We introduce SoftAE, an uncertainty-aware active exploration framework that autonomously learns task-agnostic and generalizable dynamics models of soft robotic systems. SoftAE employs probabilistic ensemble models to estimate epistemic uncertainty and actively guides exploration toward underrepresented regions of the state-action space, achieving efficient coverage of diverse behaviors without task-specific supervision. We evaluate SoftAE on three simulated soft robotic platforms — a continuum arm, an articulated fish in fluid, and a musculoskeletal leg with hybrid actuation — and on a pneumatically actuated continuum soft arm in the real world. Compared with random exploration and task-specific model-based reinforcement learning, SoftAE produces more accurate dynamics models, enables superior zero-shot control on unseen tasks, and maintains robustness under sensing noise, actuation delays, and nonlinear material effects. These results demonstrate that uncertainty-driven active exploration can yield scalable, reusable dynamics models across diverse soft robotic morphologies, representing a step toward more autonomous, adaptable, and data-efficient control in compliant robots. Read More
Cognition Envelopes for Bounded AI Reasoning in Autonomous UAS Operationscs.AI updates on arXiv.org arXiv:2510.26905v1 Announce Type: new
Abstract: Cyber-physical systems increasingly rely on Foundational Models such as Large Language Models (LLMs) and Vision-Language Models (VLMs) to increase autonomy through enhanced perception, inference, and planning. However, these models also introduce new types of errors, such as hallucinations, overgeneralizations, and context misalignments, resulting in incorrect and flawed decisions. To address this, we introduce the concept of Cognition Envelopes, designed to establish reasoning boundaries that constrain AI-generated decisions while complementing the use of meta-cognition and traditional safety envelopes. As with safety envelopes, Cognition Envelopes require practical guidelines and systematic processes for their definition, validation, and assurance.
arXiv:2510.26905v1 Announce Type: new
Abstract: Cyber-physical systems increasingly rely on Foundational Models such as Large Language Models (LLMs) and Vision-Language Models (VLMs) to increase autonomy through enhanced perception, inference, and planning. However, these models also introduce new types of errors, such as hallucinations, overgeneralizations, and context misalignments, resulting in incorrect and flawed decisions. To address this, we introduce the concept of Cognition Envelopes, designed to establish reasoning boundaries that constrain AI-generated decisions while complementing the use of meta-cognition and traditional safety envelopes. As with safety envelopes, Cognition Envelopes require practical guidelines and systematic processes for their definition, validation, and assurance. Read More
