As extreme heat events intensify due to climate change and urbanization, cities face increasing challenges in mitigating outdoor heat stress. While traditional physical models such as SOLWEIG and ENVI-met provide detailed assessments of human-perceived heat exposure, their computational demands limit scalability for city-wide planning. In this study, we propose GSM-UTCI, a multimodal deep learning framework designed to predict daytime average Universal Thermal Climate Index (UTCI) at 1-meter hyperlocal resolution. The model fuses surface morphology (nDSM), high-resolution land cover data, and hourly meteorological conditions using a feature-wise linear modulation (FiLM) architecture that dynamically conditions spatial features on atmospheric context. Trained on SOLWEIG-derived UTCI maps, GSM-UTCI achieves near-physical accuracy, with an R2 of 0.9151 and a mean absolute error (MAE) of 0.41°C, while reducing inference time from hours to under five minutes for an entire city. To demonstrate its planning relevance, we apply GSM-UTCI to simulate systematic landscape transformation scenarios in Philadelphia, replacing bare earth, grass, and impervious surfaces with tree canopy. Results show spatially heterogeneous but consistently strong cooling effects, with impervious-to-tree conversion producing the highest aggregated benefit (-4.18°C average change in UTCI across 270.7 km2). Tract-level bivariate analysis further reveals strong alignment between thermal reduction potential and land cover proportions. These findings underscore the utility of GSM-UTCI as a scalable, fine-grained decision support tool for urban climate adaptation, enabling scenario-based evaluation of greening strategies across diverse urban environments.

We propose novel classical and quantum online algorithms for learning finite-horizon and infinite-horizon average-reward Markov Decision Processes (MDPs). Our algorithms are based on a hybrid exploration-generative reinforcement learning (RL) model wherein the agent can, from time to time, freely interact with the environment in a generative sampling fashion, i.e., by having access to a "simulator". By employing known classical and new quantum algorithms for approximating optimal policies under a generative model within our learning algorithms, we show that it is possible to avoid several paradigms from RL like "optimism in the face of uncertainty" and "posterior sampling" and instead compute and use optimal policies directly, which yields better regret bounds compared to previous works. For finite-horizon MDPs, our quantum algorithms obtain regret bounds which only depend logarithmically on the number of time steps $T$, thus breaking the $O(\sqrt{T})$ classical barrier. This matches the time dependence of the prior quantum works of Ganguly et al. (arXiv'23) and Zhong et al. (ICML'24), but with improved dependence on other parameters like state space size $S$ and action space size $A$. For infinite-horizon MDPs, our classical and quantum bounds still maintain the $O(\sqrt{T})$ dependence but with better $S$ and $A$ factors. Nonetheless, we propose a novel measure of regret for infinite-horizon MDPs with respect to which our quantum algorithms have $\operatorname{poly}\log{T}$ regret, exponentially better compared to classical algorithms. Finally, we generalise all of our results to compact state spaces.

This study proposes a method that integrates convolutional neural networks (CNNs) with ensemble numerical weather prediction (NWP) models, enabling surface temperature forecasting at lead times beyond the short-range (five-day) forecast period. Owing to limited computational resources, operational medium-range temperature forecasts typically rely on low-resolution NWP models, which are prone to systematic and random errors. To resolve these limitations, the proposed method first reduces systematic errors through CNN-based post-processing (bias correction and spatial super-resolution) on each ensemble member, reconstructing high-resolution temperature fields from low-resolution model outputs. Second, it reduces random errors through ensemble averaging of the CNN-corrected members. This study also investigates whether the sequence of CNN correction and ensemble averaging affects the forecast accuracy. For comparison with the proposed method, we additionally conducted experiments with the CNN trained on ensemble-averaged forecasts. The first approach--CNN correction before ensemble averaging--consistently achieved higher accuracy than the reverse approach. Although based on low-resolution ensemble forecasts, the proposed method notably outperformed the high-resolution deterministic NWP models. These findings indicate that combining CNN-based correction with ensemble averaging effectively reduces both the systematic and random errors in NWP model outputs. The proposed approach is a practical and scalable solution for improving medium-range temperature forecasts, and is particularly valuable at operational centers with limited computational resources.

Accurate load forecasting is essential to the operation of modern electric power systems. Given the sensitivity of electricity demand to weather variability and temporal dynamics, capturing non-linear patterns is essential for long-term planning. This paper presents a comparative analysis of machine learning models, Linear Regression, XGBoost, LightGBM, and Long Short-Term Memory (LSTM), for forecasting system-wide electricity load up to one year in advance. Midterm forecasting has shown to be crucial for maintenance scheduling, resource allocation, financial forecasting, and market participation. The paper places a focus on the use of a method called "Shapley Additive Explanations" (SHAP) to improve model explainability. SHAP enables the quantification of feature contributions, guiding informed feature engineering and improving both model transparency and forecasting accuracy.

We propose a novel Decentralized Differentially Private Power Method (D-DP-PM) for performing Principal Component Analysis (PCA) in networked multi-agent settings. Unlike conventional decentralized PCA approaches where each agent accesses the full n-dimensional sample space, we address the challenging scenario where each agent observes only a subset of dimensions through row-wise data partitioning. Our method ensures $(ε,δ)$-Differential Privacy (DP) while enabling collaborative estimation of global eigenvectors across the network without requiring a central aggregator. We achieve this by having agents share only local embeddings of the current eigenvector iterate, leveraging both the inherent privacy from random initialization and carefully calibrated Gaussian noise additions. We prove that our algorithm satisfies the prescribed $(ε,δ)$-DP guarantee and establish convergence rates that explicitly characterize the impact of the network topology. Our theoretical analysis, based on linear dynamics and high-dimensional probability theory, provides tight bounds on both privacy and utility. Experiments on real-world datasets demonstrate that D-DP-PM achieves superior privacy-utility tradeoffs compared to naive local DP approaches, with particularly strong performance in moderate privacy regimes ($ε\in[2, 5]$). The method converges rapidly, allowing practitioners to trade iterations for enhanced privacy while maintaining competitive utility.

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient descent (DP-SGD) guarantees formal privacy, yet it does so at a pronounced cost: gradients are forcibly clipped and perturbed with noise, degrading sample efficiency and final accuracy. Numerous variants have been proposed to soften this trade-off, but they all share a handicap: their control knobs are hard-coded, global, and oblivious to the evolving optimization landscape. Consequently, practitioners are forced either to over-spend privacy budget in pursuit of utility, or to accept mediocre models in order to stay within privacy constraints. We present RLDP, the first framework to cast DP optimization itself as a closed-loop control problem amenable to modern deep reinforcement learning (RL). RLDP continuously senses rich statistics of the learning dynamics and acts by selecting fine-grained per parameter gradient-clipping thresholds as well as the magnitude of injected Gaussian noise. A soft actor-critic (SAC) hyper-policy is trained online during language model fine-tuning; it learns, from scratch, how to allocate the privacy budget where it matters and when it matters. Across more than 1,600 ablation experiments on GPT2-small, Llama-1B, Llama-3B, and Mistral-7B, RLDP delivers perplexity reductions of 1.3-30.5% (mean 5.4%) and an average 5.6% downstream utility gain. RLDP reaches each baseline's final utility after only 13-43% of the gradient-update budget (mean speed-up 71%), all while honoring the same ($ε$, $δ$)-DP contract and exhibiting equal or lower susceptibility to membership-inference and canary-extraction attacks.

To understand our global progress for sustainable development and disaster risk reduction in many developing economies, two recent major initiatives - the Uniform African Exposure Dataset of the Global Earthquake Model (GEM) Foundation and the Modelling Exposure through Earth Observation Routines (METEOR) Project - implemented classical spatial disaggregation techniques to generate large-scale mapping of urban morphology using the information from various satellite imagery and its derivatives, geospatial datasets of the built environment, and subnational census statistics. However, the local discrepancy with well-validated census statistics and the propagated model uncertainties remain a challenge in such coarse-to-fine-grained mapping problems, specifically constrained by weak and conditional label supervision. Therefore, we present Deep Conditional Census-Constrained Clustering (DeepC4), a novel deep learning-based spatial disaggregation approach that incorporates local census statistics as cluster-level constraints while considering multiple conditional label relationships in a joint multitask learning of the patterns of satellite imagery. To demonstrate, compared to GEM and METEOR, we enhanced the quality of Rwandan maps of urban morphology, specifically building exposure and physical vulnerability, at the third-level administrative unit from the 2022 census. As the world approaches the conclusion of our global frameworks in 2030, our work has offered a new deep learning-based mapping technique towards a spatial auditing of our existing coarse-grained derived information at large scales.

We describe a thermodynamic-inspired computing paradigm based on oscillatory neural networks (ONNs). While ONNs have been widely studied as Ising machines for tackling complex combinatorial optimization problems, this work investigates their feasibility in solving linear algebra problems, specifically the inverse matrix. Grounded in thermodynamic principles, we analytically demonstrate that the linear approximation of the coupled Kuramoto oscillator model leads to the inverse matrix solution. Numerical simulations validate the theoretical framework, and we examine the parameter regimes that computation has the highest accuracy.

In this report, we introduce Falcon-H1, a new series of large language models (LLMs) featuring hybrid architecture designs optimized for both high performance and efficiency across diverse use cases. Unlike earlier Falcon models built solely on Transformer or Mamba architectures, Falcon-H1 adopts a parallel hybrid approach that combines Transformer-based attention with State Space Models (SSMs), known for superior long-context memory and computational efficiency. We systematically revisited model design, data strategy, and training dynamics, challenging conventional practices in the field. Falcon-H1 is released in multiple configurations, including base and instruction-tuned variants at 0.5B, 1.5B, 1.5B-deep, 3B, 7B, and 34B parameters. Quantized instruction-tuned models are also available, totaling over 30 checkpoints on Hugging Face Hub. Falcon-H1 models demonstrate state-of-the-art performance and exceptional parameter and training efficiency. The flagship Falcon-H1-34B matches or outperforms models up to 70B scale, such as Qwen3-32B, Qwen2.5-72B, and Llama3.3-70B, while using fewer parameters and less data. Smaller models show similar trends: the Falcon-H1-1.5B-Deep rivals current leading 7B-10B models, and Falcon-H1-0.5B performs comparably to typical 7B models from 2024. These models excel across reasoning, mathematics, multilingual tasks, instruction following, and scientific knowledge. With support for up to 256K context tokens and 18 languages, Falcon-H1 is suitable for a wide range of applications. All models are released under a permissive open-source license, underscoring our commitment to accessible and impactful AI research.

A RL (Reinforcement Learning) algorithm was developed for command automation onboard a 3U CubeSat. This effort focused on the implementation of macro control action RL, a technique in which an onboard agent is provided with compiled information based on live telemetry as its observation. The agent uses this information to produce high-level actions, such as adjusting attitude to solar pointing, which are then translated into control algorithms and executed through lower-level instructions. Once trust in the onboard agent is established, real-time environmental information can be leveraged for faster response times and reduced reliance on ground control. The approach not only focuses on developing an RL algorithm for a specific satellite but also sets a precedent for integrating trusted AI into onboard systems. This research builds on previous work in three areas: (1) RL algorithms for issuing high-level commands that are translated into low-level executable instructions; (2) the deployment of AI inference models interfaced with live operational systems, particularly onboard spacecraft; and (3) strategies for building trust in AI systems, especially for remote and autonomous applications. Existing RL research for satellite control is largely limited to simulation-based experiments; in this work, these techniques are tailored by constructing a digital twin of a specific spacecraft and training the RL agent to issue macro actions in this simulated environment. The policy of the trained agent is copied to an isolated environment, where it is fed compiled information about the satellite to make inference predictions, thereby demonstrating the RL algorithm's validity on orbit without granting it command authority. This process enables safe comparison of the algorithm's predictions against actual satellite behavior and ensures operation within expected parameters.