Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks to enhance their proficiency. However, safety concerns are frequently overlooked during this fine-tuning process. In this work, we show that aligned LLMs can become unintentionally misaligned, leading to a higher likelihood of executing harmful tasks and a reduced tendency to refuse them when fine-tuned to execute agentic tasks. To address these safety challenges, we propose Prefix INjection Guard (PING), a simple yet effective method that prepends automatically generated natural language prefixes to agent responses, guiding them to refuse harmful requests while preserving performance on benign tasks. Specifically, we introduce an iterative approach that alternates between (1) generating candidate prefixes and (2) selecting those that optimize both task performance and refusal behavior. Experimental results demonstrate that PING significantly enhances the safety of fine-tuned LLM agents without sacrificing their effectiveness. PING consistently outperforms existing prompting approaches across diverse benchmarks in both web navigation and code generation tasks. Our analysis of internal hidden states via linear probes reveals that prefix tokens are crucial for behavior modification, explaining the performance gains. WARNING: This paper contains contents that are unethical or offensive in nature.

We introduce PINGS (Physics-Informed Neural Network for Fast Generative Sampling), a framework that amortizes diffusion sampling by training a physics-informed network to approximate reverse-time probability-flow dynamics, reducing sampling to a single forward pass (NFE = 1). As a proof of concept, we learn a direct map from a 3D standard normal to a non-Gaussian Gaussian Mixture Model (GMM). PINGS preserves the target's distributional structure (multi-bandwidth kernel $MMD^2 = 1.88 \times 10^{-2}$ with small errors in mean, covariance, skewness, and excess kurtosis) and achieves constant-time generation: $10^4$ samples in $16.54 \pm 0.56$ millisecond on an RTX 3090, versus 468-843 millisecond for DPM-Solver (10/20) and 960 millisecond for DDIM (50) under matched conditions. We also sanity-check the PINN/automatic-differentiation pipeline on a damped harmonic oscillator, obtaining MSEs down to $\mathcal{O}(10^{-5})$. Compared to fast but iterative ODE solvers and direct-map families (Flow, Rectified-Flow, Consistency), PINGS frames generative sampling as a PINN-style residual problem with endpoint anchoring, yielding a white-box, differentiable map with NFE = 1. These proof-of-concept results position PINGS as a promising route to fast, function-based generative sampling with potential extensions to scientific simulation (e.g., fast calorimetry).

This paper presents an enhanced version of the Interactive Voting-Based Map Matching algorithm, designed to efficiently process trajectories with varying sampling rates. The main aim is to reconstruct GPS trajectories with high accuracy, independent of input data quality. Building upon the original algorithm, developed exclusively for aligning GPS signals to road networks, we extend its capabilities by integrating trajectory imputation. Our improvements also include the implementation of a distance-bounded interactive voting strategy to reduce computational complexity, as well as modifications to address missing data in the road network. Furthermore, we incorporate a custom-built asset derived from OpenStreetMap, enabling this approach to be smoothly applied in any geographic region covered by OpenStreetMap's road network. These advancements preserve the core strengths of the original algorithm while significantly extending its applicability to diverse real-world scenarios.

Robots require high-fidelity reconstructions of their environment for effective operation. Such scene representations should be both, geometrically accurate and photorealistic to support downstream tasks. While this can be achieved by building distance fields from range sensors and radiance fields from cameras, the scalable incremental mapping of both fields consistently and at the same time with high quality remains challenging. In this paper, we propose a novel map representation that unifies a continuous signed distance field and a Gaussian splatting radiance field within an elastic and compact point-based implicit neural map. By enforcing geometric consistency between these fields, we achieve mutual improvements by exploiting both modalities. We devise a LiDAR-visual SLAM system called PINGS using the proposed map representation and evaluate it on several challenging large-scale datasets. Experimental results demonstrate that PINGS can incrementally build globally consistent distance and radiance fields encoded with a compact set of neural points. Compared to the state-of-the-art methods, PINGS achieves superior photometric and geometric rendering at novel views by leveraging the constraints from the distance field. Furthermore, by utilizing dense photometric cues and multi-view consistency from the radiance field, PINGS produces more accurate distance fields, leading to improved odometry estimation and mesh reconstruction.

Many iPhone users may be familiar with that heart-stopping feeling when you pat your pocket and the familiar outline of your phone isn't there. Usually, you're able to find it lying nearby, but a tech expert has revealed fail-proof ways to locate a lost iPhone if it's taking longer than usual to find it. Kurt Knutsson, also known as Kurt the Cyberguy, is the founder of The Cyberguy Report which warns viewers about possible cybersecurity scams and whether you could be a target. The Apple watch can be used to ping your iPhone if they're within 330 feet of each other He has now explained that the tools users already have access to like Siri and the Apple smartwatch are effective ways to locate your missing phone. Although iPhone users can use most Apple devices to locate their phones, there are three other options you may not have considered, according to Knutsson.

Urban mobility is on the cusp of transformation with the emergence of shared, connected, and cooperative automated vehicles. Yet, for them to be accepted by customers, trust in their punctuality is vital. Many pilot initiatives operate without a fixed schedule, thus enhancing the importance of reliable arrival time (AT) predictions. This study presents an AT prediction system for autonomous shuttles, utilizing separate models for dwell and running time predictions, validated on real-world data from five cities. Alongside established methods such as XGBoost, we explore the benefits of integrating spatial data using graph neural networks (GNN). To accurately handle the case of a shuttle bypassing a stop, we propose a hierarchical model combining a random forest classifier and a GNN. The results for the final AT prediction are promising, showing low errors even when predicting several stops ahead. Yet, no single model emerges as universally superior, and we provide insights into the characteristics of pilot sites that influence the model selection process. Finally, we identify dwell time prediction as the key determinant in overall AT prediction accuracy when autonomous shuttles are deployed in low-traffic areas or under regulatory speed limits. This research provides insights into the current state of autonomous public transport prediction models and paves the way for more data-informed decision-making as the field advances.

Side-scan sonar (SSS) is a lightweight acoustic sensor that is frequently deployed on autonomous underwater vehicles (AUVs) to provide high-resolution seafloor images. However, using side-scan images to perform simultaneous localization and mapping (SLAM) remains a challenge when there is a lack of 3D bathymetric information and discriminant features in the side-scan images. To tackle this, we propose a feature-based SLAM framework using side-scan sonar, which is able to automatically detect and robustly match keypoints between paired side-scan images. We then use the detected correspondences as constraints to optimize the AUV pose trajectory. The proposed method is evaluated on real data collected by a Hugin AUV, using as a ground truth reference both manually-annotated keypoints and a 3D bathymetry mesh from multibeam echosounder (MBES). Experimental results demonstrate that our approach is able to reduce drifts from the dead-reckoning system. The framework is made publicly available for the benefit of the community.

If you ask Psync Labs, it'll tell you the problem with smart security cameras is that they don't know what they're seeing. Those motion pings you get with other products? So, Psync's focus is to improve machine vision, but to also go one step further and pair this vision with GPT-enabled generative AI to help it, and you, understand what it can see. Its first product, the Genie S, is a security camera that'll send you a written description of what (it thinks) is going on. On paper, the Genie S has a similar feature set to plenty of other affordable home security units I could mention.

At code.store, we build amazing products for our clients using the most advanced technologies: Low Code, No Code, Blockchain, AI, and Cloud native functions. Ping us if you need help! Those 8 tools are helping our clients to reduce the tremendous workload of their teams, we wanted to share them. Jasper and Copy.ai are used by marketers and SEO experts to produce AI-generated content. But the writer's experience is terrible.

Chinese enterprises increased patent filings for artificial intelligence products rapidly in the past couple of years. The companies holding the most active AI and machine learning patent families are now tech giant Tencent and search engine provider Baidu, ahead of U.S. firm IBM, South Korea's Samsung, Chinese insurance provider Ping An and former AI patent leader Microsoft. The latter company has been seeing one of its major AI investments come to fruition recently, as conversational AI bot ChatGPT by Microsoft partner OpenAI has been making waves. Microsoft swiftly announced another round of funding for OpenAI, rumored to be to the tune of $10 billion. As this chart based on the LexisNexis PatentSight directory shows, Tencent and Baidu became the largest patent owners in machine learning and AI in 2021, each holding more than 9,000 active patent families.