arXiv:2603.02229v1 Announce Type: new Abstract: Safety post-training has been studied extensively in single-step “chat” settings where safety typically refers to refusing harmful requests. We study an “agentic” (i.e., multi-step, tool-use) setting where safety refers to harmful actions directly taken by the LLM. We compare the effects of running direct preference optimization (DPO) on safety or helpfulness alone vs both metrics sequentially. As expected, training on one metric alone results in an extreme point along this frontier. However, unlike […]

Ver mais

A Unified Namespace (UNS) gives every sensor, actuator, and PLC a path in a shared ISA-95 hierarchy. Data from every facility flows into one namespace, whether the transport is MQTT, OPC UA, or Kafka. The structure problem? Solved. But structure alone doesn’t make those paths queryable. Once you store millions of timestamped values in a dedicated time-series database, the tag_id in each row is just a reference, and the hierarchy that gives it meaning lives somewhere else. Every contextual question (“which […]

Ver mais

arXiv:2602.06152v1 Announce Type: new Abstract: Controlling waves by actively changing the material parameters of a medium enables the development of new acoustic and electrical devices. Modulating the material breaks classical properties like reciprocity and the conservation of energy, which complicates the mathematical analysis. Without a limiting amplitude principle, time-harmonic formulations are generally inapplicable. The present manuscript develops an alternative tool for the time-modulated acoustic wave equation, that is based on a modulated Fourier expansion (MFE). The solution is […]

Ver mais

arXiv:2601.14259v1 Announce Type: new Abstract: Emotion recognition is a fundamental component of next-generation human-computer interaction (HCI), enabling machines to perceive, understand, and respond to users’ affective states. However, existing systems often rely on single-modality analysis such as facial expressions, speech tone, or textual sentiment, resulting in limited robustness and poor generalization in real-world environments. To address these challenges, this study proposes a Cloud-Based Cross-Modal Transformer (CMT) framework for multimodal emotion recognition and adaptive human-computer interaction. The proposed model […]

Ver mais

arXiv:2603.26684v1 Announce Type: new Abstract: Multi-Agent Path Finding (MAPF) requires collision-free trajectories for multiple agents on a shared graph, often with the objective of minimizing the sum-of-costs (SOC). Many optimal and bounded-suboptimal solvers rely on time-expanded models and centralized conflict resolution, which limits scalability in large or dense instances. We propose a hybrid prioritized framework that separates geometric planning from execution-time conflict resolution. In the first stage, Geometric Conflict Preemption (GCP) plans agents sequentially with A* on the […]

Ver mais

arXiv:2602.16863v1 Announce Type: new Abstract: The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging class of dexterity, requiring grasping thin objects, in-hand object rotations, and forceful interactions. Since collecting teleoperation data for these behaviors is challenging, sim-to-real reinforcement learning (RL) is a promising alternative. However, prior approaches typically require substantial engineering effort to model objects and tune reward functions for each task. In this work, we […]

Ver mais