Sudan's air force has carried out bombings in which at least 1,700 civilians have died in attacks on residential neighbourhoods, markets, schools and camps for displaced people, according to an investigation into air raids in the country's civil war. The Sudan Witness Project says it has compiled the largest known dataset of military airstrikes in the conflict, which began in April 2023. Its analysis indicates that the air force has used unguided bombs in populated areas. The data focuses on attacks by warplanes, which only the Sudanese Armed Forces (SAF) is capable of operating. Its rival, the paramilitary Rapid Support Forces (RSF) does not have aircraft.

While reinforcement learning has advanced the alignment of text-to-image (T2I) models, state-of-the-art policy gradient methods are still hampered by training instability and high variance, hindering convergence speed and compromising image quality. Our analysis identifies a key cause of this instability: disproportionate credit assignment, in which the mathematical structure of the generative sampler produces volatile and non-proportional feedback across timesteps. To address this, we introduce Proportionate Credit Policy Optimization (PCPO), a framework that enforces proportional credit assignment through a stable objective reformulation and a principled reweighting of timesteps. This correction stabilizes the training process, leading to significantly accelerated convergence and superior image quality. The improvement in quality is a direct result of mitigating model collapse, a common failure mode in recursive training. PCPO substantially outperforms existing policy gradient baselines on all fronts, including the state-of-the-art DanceGRPO. Code is available at https://github.com/jaylee2000/pcpo/.

XX 1 Disturbance Compensation for Safe Kinematic Control of Robotic Systems with Closed Architecture Fan Zhang 1,2, Jinfeng Chen 1, Joseph J. B. Mvogo Ahanda 3, Hanz Richter 4, Ge Lv 5, Bin Hu 1,2, Qin Lin 1,2 Abstract--In commercial robotic systems, it is common to encounter a closed inner-loop (low-level) torque controller that is not user-modifiable. However, the outer-loop controller, which sends kinematic commands such as position or velocity for the inner-loop controller to track, is typically exposed to users. In this work, we focus on the development of an easily integrated add-on at the outer-loop layer by combining disturbance rejection control and robust control barrier function for high-performance tracking and safe control of the whole dynamic system of an industrial manipulator . This is particularly beneficial when 1) the inner-loop controller is imperfect, unmodifiable, and uncertain; and 2) the dynamic model exhibits significant uncertainty. Stability analysis, formal safety guarantee proof, simulations, and hardware experiments with a PUMA robotic manipulator are presented. Our solution demonstrates superior performance in terms of simplicity of implementation, robustness, tracking precision, and safety compared to the state of the art. I. INTRODUCTION Robotic systems often employ hierarchical software design, stacking perception, decision-making, planning, and low-level control. Such modularity is particularly beneficial for troubleshooting and improving the reliability of robotic systems. For example, in the control block, a combination of a kinematic controller (outer-loop controller) and a dynamic controller (inner-loop controller) is commonly seen in various robots. However, because tuning the inner-loop controller requires expert knowledge, this component is typically not exposed to users due to product safety considerations, a practice referred to as closed architecture in the literature [1]-[4]. In other words, users are only allowed to design the kinematic controller, sending position or velocity for the inner-loop controller to track. Additionally, mechanical parts 1 The authors are with the Department of Engineering Technology, University of Houston, USA. Corresponding author: Qin Lin, qlin21@central.uh.edu 2 Fan Zhang is also with the Department of Electrical and Computer Engineering, University of Houston, USA 3 Joseph Jean Baptiste Mvogo Ahanda is with the Department of Biomedical Engineering, The University of Ebolowa, Cameroon 4 Hanz Richter is with the Department of Mechanical Engineering, Cleveland State University, USA 5 Ge Lv is with the Department of Mechanical Engineering, Clemson University, USA. This material is based upon work supported by the National Science Foundation under Grant Nos.

Inspired by graph-based methodologies, we introduce a novel graph-spanning algorithm designed to identify changes in both offline and online data across low to high dimensions. This versatile approach is applicable to Euclidean and graph-structured data with unknown distributions, while maintaining control over error probabilities. Theoretically, we demonstrate that the algorithm achieves high detection power when the magnitude of the change surpasses the lower bound of the minimax separation rate, which scales on the order of $\sqrt{nd}$. Our method outperforms other techniques in terms of accuracy for both Gaussian and non-Gaussian data. Notably, it maintains strong detection power even with small observation windows, making it particularly effective for online environments where timely and precise change detection is critical.

Decision making often occurs in the presence of incomplete information, leading to the under- or overestimation of risk. Leveraging the observable information to learn the complete information is called nowcasting. In practice, incomplete information is often a consequence of reporting or observation delays. In this paper, we propose an expectation-maximisation (EM) framework for nowcasting that uses machine learning techniques to model both the occurrence as well as the reporting process of events. We allow for the inclusion of covariate information specific to the occurrence and reporting periods as well as characteristics related to the entity for which events occurred. We demonstrate how the maximisation step and the information flow between EM iterations can be tailored to leverage the predictive power of neural networks and (extreme) gradient boosting machines (XGBoost). With simulation experiments, we show that we can effectively model both the occurrence and reporting of events when dealing with high-dimensional covariate information. In the presence of non-linear effects, we show that our methodology outperforms existing EM-based nowcasting frameworks that use generalised linear models in the maximisation step. Finally, we apply the framework to the reporting of Argentinian Covid-19 cases, where the XGBoost-based approach again is most performant.

We introduce a constraint-programming framework for generating synthetic populations that reproduce target statistics with high precision while enforcing full individual consistency. Unlike data-driven approaches that infer distributions from samples, our method directly encodes aggregated statistics and structural relations, enabling exact control of demographic profiles without requiring any microdata. We validate the approach on official demographic sources and study the impact of distributional deviations on downstream analyses. This work is conducted within the Pollitics project developed by Emotia, where synthetic populations can be queried through large language models to model societal behaviors, explore market and policy scenarios, and provide reproducible decision-grade insights without personal data.

Real-time calibration of stochastic volatility models (SVMs) is computationally bottlenecked by the need to repeatedly solve coupled partial differential equations (PDEs). In this work, we propose DeepSVM, a physics-informed Deep Operator Network (PI-DeepONet) designed to learn the solution operator of the Heston model across its entire parameter space. Unlike standard data-driven deep learning (DL) approaches, DeepSVM requires no labelled training data. Rather, we employ a hard-constrained ansatz that enforces terminal payoffs and static no-arbitrage conditions by design. Furthermore, we use Residual-based Adaptive Refinement (RAR) to stabilize training in difficult regions subject to high gradients. Overall, DeepSVM achieves a final training loss of $10^{-5}$ and predicts highly accurate option prices across a range of typical market dynamics. While pricing accuracy is high, we find that the model's derivatives (Greeks) exhibit noise in the at-the-money (ATM) regime, highlighting the specific need for higher-order regularization in physics-informed operator learning.

We introduce ideal attribution mechanisms, a formal abstraction for reasoning about attribution decisions over strings. At the core of this abstraction lies the ledger, an append-only log of the prompt-response interaction history between a model and its user. Each mechanism produces deterministic decisions based on the ledger and an explicit selection criterion, making it well-suited to serve as a ground truth for attribution. We frame the design goal of watermarking schemes as faithful representation of ideal attribution mechanisms. This novel perspective brings conceptual clarity, replacing piecemeal probabilistic statements with a unified language for stating the guarantees of each scheme. It also enables precise reasoning about desiderata for future watermarking schemes, even when no current construction achieves them, since the ideal functionalities are specified first. In this way, the framework provides a roadmap that clarifies which guarantees are attainable in an idealized setting and worth pursuing in practice.

We study the classic problem of prediction with expert advice under the constraint of local differential privacy (LDP). In this context, we first show that a classical algorithm naturally satisfies LDP and then design two new algorithms that improve it: RW-AdaBatch and RW-Meta. For RW-AdaBatch, we exploit the limited-switching behavior induced by LDP to provide a novel form of privacy amplification that grows stronger on easier data, analogous to the shuffle model in offline learning. Drawing on the theory of random walks, we prove that this improvement carries essentially no utility cost. For RW-Meta, we develop a general method for privately selecting between experts that are themselves non-trivial learning algorithms, and we show that in the context of LDP this carries no extra privacy cost. In contrast, prior work has only considered data-independent experts. We also derive formal regret bounds that scale inversely with the degree of independence between experts. Our analysis is supplemented by evaluation on real-world data reported by hospitals during the COVID-19 pandemic; RW-Meta outperforms both the classical baseline and a state-of-the-art \textit{central} DP algorithm by 1.5-3$\times$ on the task of predicting which hospital will report the highest density of COVID patients each week.

Estimation of differences in conditional independence graphs (CIGs) of two time series Gaussian graphical models (TSGGMs) is investigated where the two TSGGMs are known to have similar structure. The TSGGM structure is encoded in the inverse power spectral density (IPSD) of the time series. In several existing works, one is interested in estimating the difference in two precision matrices to characterize underlying changes in conditional dependencies of two sets of data consisting of independent and identically distributed (i.i.d.) observations. In this paper we consider estimation of the difference in two IPSDs to characterize the underlying changes in conditional dependencies of two sets of time-dependent data. Our approach accounts for data time dependencies unlike past work. We analyze a penalized D-trace loss function approach in the frequency domain for differential graph learning, using Wirtinger calculus. We consider both convex (group lasso) and non-convex (log-sum and SCAD group penalties) penalty/regularization functions. An alternating direction method of multipliers (ADMM) algorithm is presented to optimize the objective function. We establish sufficient conditions in a high-dimensional setting for consistency (convergence of the inverse power spectral density to true value in the Frobenius norm) and graph recovery. Both synthetic and real data examples are presented in support of the proposed approaches. In synthetic data examples, our log-sum-penalized differential time-series graph estimator significantly outperformed our lasso based differential time-series graph estimator which, in turn, significantly outperformed an existing lasso-penalized i.i.d. modeling approach, with $F_1$ score as the performance metric.