Allen Institute for Artificial Intelligence

Accurate and efficient climate simulations are crucial for understanding Earth’s evolving climate. However, current General Circulation Models (GCMs) face challenges in capturing unresolved physical processes, such as cloud and convection. A common solution is to adopt Cloud-Resolving Models (CRMs), which provide more accurate results than the standard subgrid parameterization schemes typically used in GCMs. However, CRMs (also referred to as super-parameterizations, such as SPCAM) remain computationally prohibitive. Hybrid modeling, which integrates deep learning with equation-based GCMs, offers a promising alternative but often struggles with long-term stability and accuracy issues. In this work, we find that water vapor oversaturation during condensation is a key factor compromising the stability of hybrid modeling. To address this, we introduce CondensNet, a novel neural network architecture that embeds a self-adaptive physical constraint to correct unphysical condensation processes. CondensNet effectively mitigates water vapor oversaturation, enhancing simulation stability while maintaining accuracy and improving computational efficiency compared to super-parameterization schemes. We integrate CondensNet into a GCM to form PCNN-GCM (Physics-Constrained Neural Network GCM), a hybrid deep learning framework designed for long-term stable climate simulations under real-world conditions (AMIP setting). PCNN-GCM enables stable simulations over decades and achieves up to 370× speed-up compared with SPCAM, while also being faster than traditional CAM5 under GPU acceleration or CPU-only. Beyond stability and efficiency, PCNN-GCM demonstrates greater skill in capturing complex climate variability than CAM5, including tropical precipitation extremes and the Madden-Julian Oscillation (MJO), yielding results that align more closely with observations or reanalyses (e.g., ERA5, TRMM) than conventional parameterization schemes.

A consistent approach to track Long COVID symptoms at the Veterans Health Administration (VHA) was lacking. To reach consensus among clinical stakeholders on how long COVID symptoms should be assessed at VHA outpatient visits and recommend an assessment battery. Hybrid Delphi-Nominal Group approach. Members of the VHA Long COVID Field Advisory Board (FAB) and the VHA Long COVID Community of Practice (CoP) participated. Veteran stakeholders provided input. A literature review and clinician questionnaires identified 68 instruments across 14 symptom domains. In the first consensus round, FAB members excluded instruments with limited clinical usability. The remaining 25 instruments were ranked by CoP members. Multiple rounds of asynchronous voting were conducted until one instrument remained per domain. The top instruments were grouped into 3 batteries. Final consensus on a preferred battery was reached through additional voting. Veterans from the Los Angeles Veteran Engagement Panel assessed clarity, burden, and feasibility. The final battery included the Modified Yorkshire COVID-19 Rehabilitation Survey, VHA Whole Health Well-Being Signs, the Exercise Vital Signs Questionnaire, and the 2-Minute Step Test. Whole Health questions were also included to support the VHA's Whole Health System mission. Symptom-specific instruments already used in VHA routine care were not included in the final battery, as clinics already had access to them. A structured, rapid consensus process was used to identify a battery of symptom instruments to standardize Long COVID symptom assessment across VHA clinics.

Abstract Although autoregressive machine learning‐based emulators have been trained to produce stable and accurate rollouts in the climate of the present‐day and recent past, none so far have been trained to emulate the sensitivity of climate to substantial changes in or other greenhouse gases. As an initial step we couple the Ai2 Climate Emulator version 2 to a slab ocean model (hereafter ACE2‐SOM) and train it on output from a collection of equilibrium‐climate physics‐based reference simulations with varying levels of . We test it in equilibrium and non‐equilibrium climate scenarios with concentrations seen and unseen in training. ACE2‐SOM performs well in equilibrium‐climate inference with both in‐sample and out‐of‐sample concentrations, accurately reproducing the emergent time‐mean spatial patterns of surface temperature and precipitation change with doubling, tripling, or quadrupling. In addition, the vertical profile of atmospheric warming and change in extreme precipitation rates up to the 99.9999th percentile closely agree with the reference model. Non‐equilibrium‐climate inference is more challenging. With increasing gradually at a rate of 2% year −1 , ACE2‐SOM can accurately emulate the global annual mean trends of surface and lower‐to‐middle atmosphere fields but produces unphysical jumps in stratospheric fields. With an abrupt quadrupling of , ML‐controlled fields transition unrealistically quickly to the regime. In doing so they violate global energy conservation and exhibit unphysical sensitivities of surface and top of atmosphere radiative fluxes to instantaneous changes in . Future emulator development needed to address these issues should improve its generalizability to diverse climate change scenarios.

Electromagneticsoft actuator arrays (ESAAs) combine compliance with fast, controllable actuation and scalability, providing a promising foundation for the development of interconnected soft actuator arrays inspired by the structure and function of biological muscles. In this work, we present a control framework and an actuator selection strategy for an artificial soft muscle composed of ESAAs to enable accurate reference tracking. Since directly measuring the states of each ESA is often impractical in real-world applications, we first design a Kalman filter-based observer to estimate all system states from available observations. Using these estimates, we develop a Linear Quadratic Gaussian (LQG) controller to achieve reference tracking. Since thermal buildup from constant use can damage the actuators, we consider whether switching between different subsets of active actuators could offer thermal relief. While actuator switching intuitively suggests reduced heating by providing resting periods, our investigation reveals that this strategy can lead to higher thermal accumulation compared to the continuous mode. This is because we need substantially larger control effort when we have fewer active actuators in the switching mode, which, in the absence of effective active cooling, fail to provide sufficient heat dissipation during operation. Simulation results are presented to demonstrate the effectiveness of the proposed method in achieving the trajectory objective and to explore how switching affects the system’s thermal profile, revealing a trade-off between tracking performance and heat generation.

Developing robotic hands that adapt to real-world dynamics remains a fundamental challenge in robotics and machine intelligence. Despite notable advances in replicating human-hand kinematics and control algorithms, robotic systems still struggle to match human capabilities in dynamic environments, primarily due to inadequate tactile feedback. To bridge this gap, we present F-TAC Hand, a biomimetic hand featuring high-resolution tactile sensing (0.1-mm spatial resolution) across 70% of its surface area. Through optimized hand design, we overcome traditional challenges in integrating high-resolution tactile sensors while preserving the full range of motion. The hand, powered by our generative algorithm that synthesizes human-like hand configurations, demonstrates robust grasping capabilities in dynamic real-world conditions. Extensive evaluation across 600 real-world trials demonstrates that this tactile-embodied system significantly outperforms non-tactile-informed alternatives in complex manipulation tasks (P < 0.0001). These results provide empirical evidence for the critical role of rich tactile embodiment in developing advanced robotic intelligence, offering promising perspectives on the relationship between physical sensing capabilities and intelligent behaviour.

IntroductionMarket-driven poaching and unsustainable wildlife harvest are significant drivers of population decline for numerous plant and animal species, including high-profile species like Asian and African elephants, wild cats, sharks and rays, and pangolins. This publication reviews the emerging role of conservation technology in combating this trade.Technologies and applicationsWe showcase how innovative technological tools are revolutionizing the detection and disruption of illegal and unsustainable wildlife trade, with a focus on those available to frontline staff working to prevent poaching and trafficking from source sites. We consider a diverse array of deployed technologies ranging from open-source software platforms, AI, and mobile apps to cutting-edge hardware, including camera traps, acoustic sensors, and remote sensing tools.Case studiesTo demonstrate the complex threats posed by IUWT to wildlife and the consequent need for tailored solutions, we present two case studies, one terrestrial and one marine, showcasing the importance of appropriate suites of technology tools for conservation implementation.DiscussionTechnology has potential to empower rangers, park staff, wildlife and fisheries inspectors, customs officials, police, and conservation practitioners with unprecedented capabilities to monitor threatened wildlife, detect illegal activities, gather evidence, and support law enforcement interventions.

Digital pathology and artificial intelligence (AI) hold immense transformative potential to revolutionize cancer diagnostics, treatment outcomes, and biomarker discovery. Gaining a deeper understanding of deep learning algorithm methods applied to histopathological data and evaluating their performance on different tasks is crucial for developing the next generation of AI technologies. To this end, we developed AI in Histopathology Explorer (HistoPathExplorer); an interactive dashboard with intelligent tools available at www.histopathexpo.ai. This real-time online resource enables users, including researchers, decision-makers, and various stakeholders, to assess the current landscape of AI applications for specific clinical tasks, analyze their performance, and explore the factors influencing their translation into practice. Moreover, a quality index was defined for evaluating the comprehensiveness of methodological details in published AI methods. HistoPathExplorer highlights opportunities and challenges for AI in histopathology, and offers a valuable resource for creating more effective methods and shaping strategies and guidelines for translating digital pathology applications into clinical practice.

As our society adopts increasingly powerful artificial intelligence (AI) systems for pervasive use, there are growing concerns about machine morality—or lack thereof. Millions of users already rely on the outputs of AI systems, such as chatbots, as decision aids. Meanwhile, AI researchers continue to grapple with the challenge of aligning these systems with human morality and values. In response to this challenge, we build and test Delphi, an open-source AI system trained to predict the moral judgements of US participants. The computational framework of Delphi is grounded in the framework proposed by the prominent moral philosopher John Rawls. Our results speak to the promises and limits of teaching machines about human morality. Delphi demonstrates improved generalization capabilities over those exhibited by off-the-shelf neural language models. At the same time, Delphi’s failures also underscore important challenges in this arena. For instance, Delphi has limited cultural awareness and is susceptible to pervasive biases. Despite these shortcomings, we demonstrate several compelling use cases of Delphi, including its incorporation as a component within an ensemble of AI systems. Finally, we computationally demonstrate the potential of Rawls’s prospect of hybrid approaches for reliable moral reasoning, inspiring future research in computational morality.