Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a condition often violated due to annotation noise, bias, or limited coverage. This misalignment can lead to undesirable behaviors, where models optimize for flawed signals rather than true human values. In this paper, we investigate a novel framework to identify and mitigate such misalignment by treating the fine-tuning process as a form of knowledge integration. We focus on detecting instances of proxy-policy conflicts, cases where the base model strongly disagrees with the proxy. We argue that such conflicts often signify areas of shared ignorance, where neither the policy nor the reward model possesses sufficient knowledge, making them especially susceptible to misalignment. To this end, we propose two complementary metrics for identifying these conflicts: a localized Proxy-Policy Alignment Conflict Score (PACS) and a global Kendall-Tau Distance measure. Building on this insight, we design an algorithm named Selective Human-in-the-loop Feedback via Conflict-Aware Sampling (SHF-CAS) that targets high-conflict QA pairs for additional feedback, refining both the reward model and policy efficiently. Experiments on two alignment tasks demonstrate that our approach enhances general alignment performance, even when trained with a biased proxy reward. Our work provides a new lens for interpreting alignment failures and offers a principled pathway for targeted refinement in LLM training.

Recent advances in multi-modal models have demonstrated strong performance in tasks such as image generation and reasoning. However, applying these models to the fire domain remains challenging due to the lack of publicly available datasets with high-quality fire domain annotations. To address this gap, we introduce $\textbf{DetectiumFire}$, a large-scale, multi-modal dataset comprising of 22.5k high-resolution fire-related images and 2.5k real-world fire-related videos covering a wide range of fire types, environments, and risk levels. The data are annotated with both traditional computer vision labels (e.g., bounding boxes) and detailed textual prompts describing the scene, enabling applications such as synthetic data generation and fire risk reasoning. DetectiumFire offers clear advantages over existing benchmarks in scale, diversity, and data quality, significantly reducing redundancy and enhancing coverage of real-world scenarios. We validate the utility of DetectiumFire across multiple tasks, including object detection, diffusion-based image generation, and vision-language reasoning. Our results highlight the potential of this dataset to advance fire-related research and support the development of intelligent safety systems. We release DetectiumFire to promote broader exploration of fire understanding in the AI community.

This article presents a method to create a digital twin for sauna. The digital twin deploys a data analytics method based on fuzzy similarity measure for data summarization to provide real-time actionable instructions. The intended outcome of the digital twin is enhanced safety and improved sauna experience. In this research, we collected the data through experimentation with a testbed and interviews. Our implemented digital twin simplifies the readings of nineteen sensors into a single graphical form for the user that illustrates the overall sauna conditions and assists the sauna manager with condition optimization. Results illustrated the effectiveness of the digital twin in achieving an enhanced sauna condition for the users and providing the sauna manager with a decision support system. The method of creating the digital twin described in this article has potential implications for the condition monitoring, predictive maintenance, and enhancing the safety and security of complex systems.

In this paper, a use case related to smart buildings is presented to illustrate the application of IoT-enabled workplaces. The data collected from two office spaces are compared using efficient data analytics method. For this comparison, the environmental factors considered are temperature, humidity, air quality, and workplace particle numbers. This paper demonstrates how to build IoT-enabled workplaces and illustrates its actual benefits to energy management and remote systems monitoring and control. A survey was conducted by the Department of Industrial Engineering and Management at Aalto University, and responses were submitted from 50 unique users to illustrate the incentives regarding IoT-enabled workplaces and to study occupants' preferences. Moreover, the research results contribute to the facility management of companies and organizations by suggesting novel methods for providing more efficient and effective IoT-enabled workplaces.