The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety

Multi-agent systems provide mature methodologies for role decomposition, coordination, and normative governance, capabilities that remain essential as increasingly powerful autonomous decision components are embedded within agent-based systems. While learned and generative models substantially expand system capability, their safety behavior is often entangled with training, making it opaque, difficult to audit, and costly to update after deployment. This paper formalizes the Alignment Flywheel as a governance-centric hybrid MAS architecture that decouples decision generation from safety governance. A Proposer, representing any autonomous decision component, generates candidate trajectories, while a Safety Oracle returns raw safety signals through a stable interface. An enforcement layer applies explicit risk policy at runtime, and a governance MAS supervises the Oracle through auditing, uncertainty-driven verification, and versioned refinement. The central engineering principle is patch locality: many newly observed safety failures can be mitigated by updating the governed oracle artifact and its release pipeline rather than retracting or retraining the underlying decision component. The architecture is implementation-agnostic with respect to both the Proposer and the Safety Oracle, and specifies the roles, artifacts, protocols, and release semantics needed for runtime gating, audit intake, signed patching, and staged rollout across distributed deployments. The result is a hybrid MAS engineering framework for integrating highly capable but fallible autonomous systems under explicit, version-controlled, and auditable oversight.

Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment

AI alignment is growing in importance, yet current approaches suffer from a critical structural flaw that entangles the safety objectives with the agent's policy. Methods such as Reinforcement Learning from Human Feedback and Direct Preference Optimization create opaque, single-use alignment artifacts, which we term Alignment Waste. We propose Interactionless Inverse Reinforcement Learning to decouple alignment artifact learning from policy optimization, producing an inspectable, editable, and model-agnostic reward model. Additionally, we introduce the Alignment Flywheel, a human-in-the-loop lifecycle that iteratively hardens the reward model through automated audits and refinement. This architecture transforms safety from a disposable expense into a durable, verifiable engineering asset.

Efficient On-Board Processing of Oblique UAV Video for Rapid Flood Extent Mapping

Effective disaster response relies on rapid disaster response, where oblique aerial video is the primary modality for initial scouting due to its ability to maximize spatial coverage and situational awareness in limited flight time. However, the on-board processing of high-resolution oblique streams is severely bottlenecked by the strict Size, Weight, and Power (SWaP) constraints of Unmanned Aerial Vehicles (UAVs). The computational density required to process these wide-field-of-view streams precludes low-latency inference on standard edge hardware. To address this, we propose Temporal Token Reuse (TTR), an adaptive inference framework capable of accelerating video segmentation on embedded devices. TTR exploits the intrinsic spatiotemporal redundancy of aerial video by formulating image patches as tokens; it utilizes a lightweight similarity metric to dynamically identify static regions and propagate their precomputed deep features, thereby bypassing redundant backbone computations. We validate the framework on standard benchmarks and a newly curated Oblique Floodwater Dataset designed for hydrological monitoring. Experimental results on edge-grade hardware demonstrate that TTR achieves a 30% reduction in inference latency with negligible degradation in segmentation accuracy (< 0.5% mIoU). These findings confirm that TTR effectively shifts the operational Pareto frontier, enabling high-fidelity, real-time oblique video understanding for time-critical remote sensing missions

Privacy-Preserving Computer Vision for Industry: Three Case Studies in Human-Centric Manufacturing

The adoption of AI-powered computer vision in industry is often constrained by the need to balance operational utility with worker privacy. Building on our previously proposed privacy-preserving framework, this paper presents its first comprehensive validation on real-world data collected directly by industrial partners in active production environments. We evaluate the framework across three representative use cases: woodworking production monitoring, human-aware AGV navigation, and multi-camera ergonomic risk assessment. The approach employs learned visual transformations that obscure sensitive or task-irrelevant information while retaining features essential for task performance. Through both quantitative evaluation of the privacy-utility trade-off and qualitative feedback from industrial partners, we assess the framework's effectiveness, deployment feasibility, and trust implications. Results demonstrate that task-specific obfuscation enables effective monitoring with reduced privacy risks, establishing the framework's readiness for real-world adoption and providing cross-domain recommendations for responsible, human-centric AI deployment in industry.

In-Field Mapping of Grape Yield and Quality with Illumination-Invariant Deep Learning

This paper presents an end-to-end, IoT-enabled robotic system for the non-destructive, real-time, and spatially-resolved mapping of grape yield and quality (Brix, Acidity) in vineyards. The system features a comprehensive analytical pipeline that integrates two key modules: a high-performance model for grape bunch detection and weight estimation, and a novel deep learning framework for quality assessment from hyperspectral (HSI) data. A critical barrier to in-field HSI is the ``domain shift" caused by variable illumination. To overcome this, our quality assessment is powered by the Light-Invariant Spectral Autoencoder (LISA), a domain-adversarial framework that learns illumination-invariant features from uncalibrated data. We validated the system's robustness on a purpose-built HSI dataset spanning three distinct illumination domains: controlled artificial lighting (lab), and variable natural sunlight captured in the morning and afternoon. Results show the complete pipeline achieves a recall (0.82) for bunch detection and a $R^2$ (0.76) for weight prediction, while the LISA module improves quality prediction generalization by over 20% compared to the baselines. By combining these robust modules, the system successfully generates high-resolution, georeferenced data of both grape yield and quality, providing actionable, data-driven insights for precision viticulture.

Enabling Privacy-Aware AI-Based Ergonomic Analysis

Musculoskeletal disorders (MSDs) are a leading cause of injury and productivity loss in the manufacturing industry, incurring substantial economic costs. Ergonomic assessments can mitigate these risks by identifying workplace adjustments that improve posture and reduce strain. Camera-based systems offer a non-intrusive, cost-effective method for continuous ergonomic tracking, but they also raise significant privacy concerns. To address this, we propose a privacy-aware ergonomic assessment framework utilizing machine learning techniques. Our approach employs adversarial training to develop a lightweight neural network that obfuscates video data, preserving only the essential information needed for human pose estimation. This obfuscation ensures compatibility with standard pose estimation algorithms, maintaining high accuracy while protecting privacy. The obfuscated video data is transmitted to a central server, where state-of-the-art keypoint detection algorithms extract body landmarks. Using multi-view integration, 3D keypoints are reconstructed and evaluated with the Rapid Entire Body Assessment (REBA) method. Our system provides a secure, effective solution for ergonomic monitoring in industrial environments, addressing both privacy and workplace safety concerns.

Adaptive Clustering for Efficient Phenotype Segmentation of UAV Hyperspectral Data

Unmanned Aerial Vehicles (UAVs) combined with Hyperspectral imaging (HSI) offer potential for environmental and agricultural applications by capturing detailed spectral information that enables the prediction of invisible features like biochemical leaf properties. However, the data-intensive nature of HSI poses challenges for remote devices, which have limited computational resources and storage. This paper introduces an Online Hyperspectral Simple Linear Iterative Clustering algorithm (OHSLIC) framework for real-time tree phenotype segmentation. OHSLIC reduces inherent noise and computational demands through adaptive incremental clustering and a lightweight neural network, which phenotypes trees using leaf contents such as chlorophyll, carotenoids, and anthocyanins. A hyperspectral dataset is created using a custom simulator that incorporates realistic leaf parameters, and light interactions. Results demonstrate that OHSLIC achieves superior regression accuracy and segmentation performance compared to pixel- or window-based methods while significantly reducing inference time. The method`s adaptive clustering enables dynamic trade-offs between computational efficiency and accuracy, paving the way for scalable edge-device deployment in HSI applications.

Predicting change in time production -- A machine learning approach to time perception

Time perception research has advanced significantly over the years. However, some areas remain largely unexplored. This study addresses two such under-explored areas in timing research: (1) A quantitative analysis of time perception at an individual level, and (2) Time perception in an ecological setting. In this context, we trained a machine learning model to predict the direction of change in an individual's time production. The model's training data was collected using an ecologically valid setup. We moved closer to an ecological setting by conducting an online experiment with 995 participants performing a time production task that used naturalistic videos (no audio) as stimuli. The model achieved an accuracy of 61%. This was 10 percentage points higher than the baseline models derived from cognitive theories of timing. The model performed equally well on new data from a second experiment, providing evidence of its generalization capabilities. The model's output analysis revealed that it also contained information about the magnitude of change in time production. The predictions were further analysed at both population and individual level. It was found that a participant's previous timing performance played a significant role in determining the direction of change in time production. By integrating attentional-gate theories from timing research with feature importance techniques from machine learning, we explained model predictions using cognitive theories of timing. The model and findings from this study have potential applications in systems involving human-computer interactions where understanding and predicting changes in user's time perception can enable better user experience and task performance.

Reward Machine Inference for Robotic Manipulation

Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have enabled robot agents to accomplish complex tasks. Reward Machines (RMs) enhance RL's capability to train policies over extended time horizons by structuring high-level task information. In this work, we introduce a novel LfD approach for learning RMs directly from visual demonstrations of robotic manipulation tasks. Unlike previous methods, our approach requires no predefined propositions or prior knowledge of the underlying sparse reward signals. Instead, it jointly learns the RM structure and identifies key high-level events that drive transitions between RM states. We validate our method on vision-based manipulation tasks, showing that the inferred RM accurately captures task structure and enables an RL agent to effectively learn an optimal policy.

Mitigating Bias Using Model-Agnostic Data Attribution

Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of images containing significant information about bias attributes. Our method utilizes a model-agnostic approach to extract pixel attributions by employing a convolutional neural network (CNN) classifier trained on small image patches. By training the classifier to predict a property of the entire image using only a single patch, we achieve region-based attributions that provide insights into the distribution of important information across the image. We propose utilizing these attributions to introduce targeted noise into datasets with confounding attributes that bias the data, thereby constraining neural networks from learning these biases and emphasizing the primary attributes. Our approach demonstrates its efficacy in enabling the training of unbiased classifiers on heavily biased datasets.