Large language models (LLMs) have advanced information extraction (IE) by enabling zeroshot and few-shot named entity recognition (NER), yet their generative outputs still show persistent and systematic errors.Despite progress through instruction fine-tuning, zeroshot NER still lags far behind supervised systems.These recurring errors mirror inconsistencies observed in early-stage human annotation processes that resolve disagreements through pilot annotation.Motivated by this analogy, we introduce DiZiNER (Disagreementguided Instruction Refinement via Pilot Annotation Simulation for Zero-shot Named Entity Recognition), a framework that simulates the pilot annotation process, employing LLMs to act as both annotators and supervisors.Multiple heterogeneous LLMs annotate shared texts, and a supervisor model analyzes intermodel disagreements to refine task instructions.Across 18 benchmarks, DiZiNER achieves zero-shot SOTA results on 14 datasets, improving prior bests by +8.0 F1 and reducing the zero-shot to supervised gap by over +11 points.It also consistently outperforms its supervisor, GPT-5 mini, indicating that improvements stem from disagreement-guided instruction refinement rather than model capacity.Pairwise agreement between models shows a strong correlation with NER performance, further supporting this finding.1

The deep neural network (DNN) model for computer vision tasks (object detection and classification) is widely used in autonomous vehicles, such as driverless cars and unmanned aerial vehicles. However, DNN models are shown to be vulnerable to adversarial image perturbations. The generation of adversarial examples against inferences of DNNs has been actively studied recently. The generation typically relies on optimizations taking an entire image frame as the decision variable. Hence, given a new image, the computationally expensive optimization needs to start over as there is no learning between the independent optimizations. Very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous vehicles, their mission, and the environment. The article presents a multi-level reinforcement learning framework that can effectively generate adversarial perturbations to misguide autonomous vehicles’ missions. In the existing image attack methods against autonomous vehicles, optimization steps are repeated for every image frame. This framework removes the need for fully converged optimization at every frame. Using multi-level reinforcement learning, we integrate a state estimator and a generative adversarial network that generates the adversarial perturbations. Due to the reinforcement learning agent consisting of state estimator, actor, and critic that only uses image streams, the proposed framework can misguide the vehicle to increase the adversary’s reward without knowing the states of the vehicle and the environment. Simulation studies and a robot demonstration are provided to validate the proposed framework’s performance.

This article examines how people respond to the presence of a flying robot under various operating conditions using traditional human physiological measures and a novel head movement measurement. A central issue to the integration of flying robotic systems into human-populated environments is how to improve the level of comfort and safety for people around them. Traditional motion control algorithms in robotics tend to focus on the actual safety of collision avoidance. However, people's perceived safety is not necessarily equivalent to the actual safety of the vehicle. Therefore flight control systems must account for people's perception of safety beyond the actual safety of the aerial vehicles in order to allow for successful interaction between humans and the unmanned aerial vehicles (UAVs). Across three experiments participants passively observed quadrotor trajectories in a simulated virtual reality environment. Quadrotor flight characteristics were manipulated in terms of speed, altitude, and audibility to examine their effect on physiological arousal and head motion kinematics. Physiological arousal was greater when the quadrotor was flying with the audio on than off, and at eye-height than overhead, and decreased over repeated exposure. In addition, head acceleration away from the UAVs indicating defensive behavior was stronger for faster speed and audible UAVs. These data suggest head acceleration can serve as a new index specific for measuring perceived safety. Applications intended for human comfort need to consider constraints from specific measures of perceived safety in addition to traditional measures of general physiological arousal.

In this article, we present a preliminary motion planning framework for a cyber-physical system consisting of a human and a flying robot in vicinity. The motion planning of the flying robot takes into account the human’s safety perception. We aim to determine a parametric model for the human’s safety perception based on test data. We use virtual reality as a safe testing environment to collect safety perception data reflected on galvanic skin response (GSR) from the test subjects experiencing a flying robot in their vicinity. The GSR signal contains both meaningful information driven by the interaction with the robot and also disturbances from unknown factors. To address the issue, we use two parametric models to approximate the GSR data: (1) a function of the robot’s position and velocity and (2) a random distribution. Intuitively, we need to choose the more likely model given the data. When GSR is statistically independent of the flying robot, then the random distribution should be selected instead of the function of the robot’s position and velocity. We implement the intuitive idea under the framework of hidden Markov model (HMM) estimation. As a result, the proposed HMM-based model improves the likelihood compared to the Gaussian noise model, which does not make a distinction between relevant and irrelevant samples due to unknown factors. We also present a numerical optimal path planning method that considers the safety perception model while ensuring spatial separation from the obstacle despite the time discretization. Optimal paths generated using the proposed model result in a reasonably safe distance from the human. In contrast, the trajectories generated by the standard regression model with the Gaussian noise assumption, without consideration of unknown factors, have undesirable shapes.