BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling

Face retouching requires removing subtle imperfections while preserving unique facial identity features, in order to enhance overall aesthetic appeal. However, existing methods suffer from a fundamental trade-off. Supervised learning on labeled data is constrained to pixel-level label mimicry, failing to capture complex subjective human aesthetic preferences. Conversely, while online reinforcement learning (RL) excels at preference alignment, its stochastic exploration paradigm conflicts with the high-fidelity demands of face retouching and often introduces noticeable noise artifacts due to accumulated stochastic drift. To address these limitations, we propose BeautyGRPO, a reinforcement learning framework that aligns face retouching with human aesthetic preferences. We construct FRPref-10K, a fine-grained preference dataset covering five key retouching dimensions, and train a specialized reward model capable of evaluating subtle perceptual differences. To reconcile exploration and fidelity, we introduce Dynamic Path Guidance (DPG). DPG stabilizes the stochastic sampling trajectory by dynamically computing an anchor-based ODE path and replanning a guided trajectory at each sampling timestep, effectively correcting stochastic drift while maintaining controlled exploration. Extensive experiments show that BeautyGRPO outperforms both specialized face retouching methods and general image editing models, achieving superior texture quality, more accurate blemish removal, and overall results that better align with human aesthetic preferences.

Bending the Scaling Law Curve in Large-Scale Recommendation Systems

Learning from user interaction history through sequential models has become a cornerstone of large-scale recommender systems. Recent advances in large language models have revealed promising scaling laws, sparking a surge of research into long-sequence modeling and deeper architectures for recommendation tasks. However, many recent approaches rely heavily on cross-attention mechanisms to address the quadratic computational bottleneck in sequential modeling, which can limit the representational power gained from self-attention. We present ULTRA-HSTU, a novel sequential recommendation model developed through end-to-end model and system co-design. By innovating in the design of input sequences, sparse attention mechanisms, and model topology, ULTRA-HSTU achieves substantial improvements in both model quality and efficiency. Comprehensive benchmarking demonstrates that ULTRA-HSTU achieves remarkable scaling efficiency gains -- over 5x faster training scaling and 21x faster inference scaling compared to conventional models -- while delivering superior recommendation quality. Our solution is fully deployed at scale, serving billions of users daily and driving significant 4% to 8% consumption and engagement improvements in real-world production environments.

LEO Constellations as a Decentralized GNSS Network: Optimizing PNT Corrections in Space

With the rapid expansion of low Earth orbit (LEO) constellations, thousands of satellites are now in operation, many equipped with onboard GNSS receivers capable of continuous orbit determination and time synchronization. This development is creating an unprecedented spaceborne GNSS network, offering new opportunities for network-driven precise LEO orbit and clock estimation. Yet, current onboard GNSS processing is largely standalone and often insufficient for high-precision applications, while centralized fusion is challenging due to computational bottlenecks and the lack of in-orbit infrastructure. In this work, we report a decentralized GNSS network over large-scale LEO constellations, where each satellite processes its own measurements while exchanging compact information with neighboring nodes to enable precise orbit and time determination. We model the moving constellation as a dynamic graph and tailor a momentum-accelerated gradient tracking (GT) method to ensure steady convergence despite topology changes. Numerical simulations with constellations containing hundreds of satellites show that the proposed method matches the accuracy of an ideal centralized benchmark, while substantially reducing communication burdens. Ultimately, this framework supports the development of autonomous and self-organizing space systems, enabling high-precision navigation with reduced dependence on continuous ground contact.

Decentralized GNSS at Global Scale via Graph-Aware Diffusion Adaptation

Network-based Global Navigation Satellite Systems (GNSS) underpin critical infrastructure and autonomous systems, yet typically rely on centralized processing hubs that limit scalability, resilience, and latency. Here we report a global-scale, decentralized GNSS architecture spanning hundreds of ground stations. By modeling the receiver network as a time-varying graph, we employ a deep linear neural network approach to learn topology-aware mixing schedules that optimize information exchange. This enables a gradient tracking diffusion strategy wherein stations execute local inference and exchange succinct messages to achieve two concurrent objectives: centimeter-level self-localization and network-wide consensus on satellite correction products. The consensus products are broadcast to user receivers as corrections, supporting precise point positioning (PPP) and precise point positioning-real-time kinematic (PPP-RTK). Numerical results demonstrate that our method matches the accuracy of centralized baselines while significantly outperforming existing decentralized methods in convergence speed and communication overhead. By reframing decentralized GNSS as a networked signal processing problem, our results pave the way for integrating decentralized optimization, consensus-based inference, and graph-aware learning as effective tools in operational satellite navigation.

3One2: One-step Regression Plus One-step Diffusion for One-hot Modulation in Dual-path Video Snapshot Compressive Imaging

Video snapshot compressive imaging (SCI) captures dynamic scene sequences through a two-dimensional (2D) snapshot, fundamentally relying on optical modulation for hardware compression and the corresponding software reconstruction. While mainstream video SCI using random binary modulation has demonstrated success, it inevitably results in temporal aliasing during compression. One-hot modulation, activating only one sub-frame per pixel, provides a promising solution for achieving perfect temporal decoupling, thereby alleviating issues associated with aliasing. However, no algorithms currently exist to fully exploit this potential. To bridge this gap, we propose an algorithm specifically designed for one-hot masks. First, leveraging the decoupling properties of one-hot modulation, we transform the reconstruction task into a generative video inpainting problem and introduce a stochastic differential equation (SDE) of the forward process that aligns with the hardware compression process. Next, we identify limitations of the pure diffusion method for video SCI and propose a novel framework that combines one-step regression initialization with one-step diffusion refinement. Furthermore, to mitigate the spatial degradation caused by one-hot modulation, we implement a dual optical path at the hardware level, utilizing complementary information from another path to enhance the inpainted video. To our knowledge, this is the first work integrating diffusion into video SCI reconstruction. Experiments conducted on synthetic datasets and real scenes demonstrate the effectiveness of our method.

Design and Implementation of a High-Precision Wind-Estimation UAV with Onboard Sensors

Accurate real-time wind vector estimation is essential for enhancing the safety, navigation accuracy, and energy efficiency of unmanned aerial vehicles (UAVs). Traditional approaches rely on external sensors or simplify vehicle dynamics, which limits their applicability during agile flight or in resource-constrained platforms. This paper proposes a real-time wind estimation method based solely on onboard sensors. The approach first estimates external aerodynamic forces using a disturbance observer (DOB), and then maps these forces to wind vectors using a thin-plate spline (TPS) model. A custom-designed wind barrel mounted on the UAV enhances aerodynamic sensitivity, further improving estimation accuracy. The system is validated through comprehensive experiments in wind tunnels, indoor and outdoor flights. Experimental results demonstrate that the proposed method achieves consistently high-accuracy wind estimation across controlled and real-world conditions, with speed RMSEs as low as \SI{0.06}{m/s} in wind tunnel tests, \SI{0.22}{m/s} during outdoor hover, and below \SI{0.38}{m/s} in indoor and outdoor dynamic flights, and direction RMSEs under \ang{7.3} across all scenarios, outperforming existing baselines. Moreover, the method provides vertical wind estimates -- unavailable in baselines -- with RMSEs below \SI{0.17}{m/s} even during fast indoor translations.

Contact SLAM: An Active Tactile Exploration Policy Based on Physical Reasoning Utilized in Robotic Fine Blind Manipulation Tasks

Contact-rich manipulation is difficult for robots to execute and requires accurate perception of the environment. In some scenarios, vision is occluded. The robot can then no longer obtain real-time scene state information through visual feedback. This is called ``blind manipulation". In this manuscript, a novel physically-driven contact cognition method, called ``Contact SLAM", is proposed. It estimates the state of the environment and achieves manipulation using only tactile sensing and prior knowledge of the scene. To maximize exploration efficiency, this manuscript also designs an active exploration policy. The policy gradually reduces uncertainties in the manipulation scene. The experimental results demonstrated the effectiveness and accuracy of the proposed method in several contact-rich tasks, including the difficult and delicate socket assembly task and block-pushing task.

Positioning Using LEO Satellite Communication Signals Under Orbital Errors

Low Earth orbit (LEO) satellites offer a promising alternative to global navigation satellite systems for precise positioning; however, their relatively low altitudes make them more susceptible to orbital perturbations, which in turn degrade positioning accuracy. In this work, we study LEO-based positioning under orbital errors within a signal-of-opportunity framework. First, we introduce a LEO orbit model that accounts for Earth's non-sphericity and derive a wideband communication model that captures fast- and slow-time Doppler effects and multipath propagation. Subsequently, we perform a misspecified Cramér-Rao bound (MCRB) analysis to evaluate the impact of orbital errors on positioning performance. Then, we propose a two-stage positioning method starting with a (i) MCRB-based weighted orbit calibration, followed by (ii) least-squares user positioning using the corrected orbit. The MCRB analysis indicates that orbital errors can induce kilometer-level position biases. Extensive simulations show that the proposed estimator can considerably enhance the positioning accuracy relative to the orbit-mismatched baseline, yielding errors on the order of a few meters.

SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification

The rapid advancement of deep neural networks (DNNs) heavily relies on large-scale, high-quality datasets. However, unauthorized commercial use of these datasets severely violates the intellectual property rights of dataset owners. Existing backdoor-based dataset ownership verification methods suffer from inherent limitations: poison-label watermarks are easily detectable due to label inconsistencies, while clean-label watermarks face high technical complexity and failure on high-resolution images. Moreover, both approaches employ static watermark patterns that are vulnerable to detection and removal. To address these issues, this paper proposes a sample-specific clean-label backdoor watermarking (i.e., SSCL-BW). By training a U-Net-based watermarked sample generator, this method generates unique watermarks for each sample, fundamentally overcoming the vulnerability of static watermark patterns. The core innovation lies in designing a composite loss function with three components: target sample loss ensures watermark effectiveness, non-target sample loss guarantees trigger reliability, and perceptual similarity loss maintains visual imperceptibility. During ownership verification, black-box testing is employed to check whether suspicious models exhibit predefined backdoor behaviors. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method and its robustness against potential watermark removal attacks.

Breaking Android with AI: A Deep Dive into LLM-Powered Exploitation

The rapid evolution of Artificial Intelligence (AI) and Large Language Models (LLMs) has opened up new opportunities in the area of cybersecurity, especially in the exploitation automation landscape and penetration testing. This study explores Android penetration testing automation using LLM-based tools, especially PentestGPT, to identify and execute rooting techniques. Through a comparison of the traditional manual rooting process and exploitation methods produced using AI, this study evaluates the efficacy, reliability, and scalability of automated penetration testing in achieving high-level privilege access on Android devices. With the use of an Android emulator (Genymotion) as the testbed, we fully execute both traditional and exploit-based rooting methods, automating the process using AI-generated scripts. Secondly, we create a web application by integrating OpenAI's API to facilitate automated script generation from LLM-processed responses. The research focuses on the effectiveness of AI-enabled exploitation by comparing automated and manual penetration testing protocols, by determining LLM weaknesses and strengths along the way. We also provide security suggestions of AI-enabled exploitation, including ethical factors and potential misuse. The findings exhibit that while LLMs can significantly streamline the workflow of exploitation, they need to be controlled by humans to ensure accuracy and ethical application. This study adds to the increasing body of literature on AI-powered cybersecurity and its effect on ethical hacking, security research, and mobile device security.