Search for: All records

Low-income households (LIH), exposed to the uncertain modern grid, bear greater energy burdens and face inequitable access to reliable power compared to high-income households (HIH). This paper proposes a two-stage stochastic community-based microgrid planning (CMP) framework to boost energy justice within the system. To reduce the negative impact of income levels, a weighted energy cost model for households within the microgrid (MG) is designed. To address the multisource uncertainty during the operation period, a two-stage stochastic framework is developed. Moreover, to assess the proposed method, the unbalanced IEEE 123 node system is employed and modified as an isolated MG. The analysis reveals the proposed model can achieve a risk-averse solution while economic optimality is guaranteed. Additionally, the designed weighted method improves the LIH’s impact rate to 67.95% and decreases the total planning cost by 22.43%. 

Low-income households (LIH), exposed to the uncertain modern grid, bear greater energy burdens and face inequitable access to reliable power compared to high-income households (HIH). This paper proposes a two-stage stochastic community-based microgrid planning (CMP) framework to boost energy justice within the system. To reduce the negative impact of income levels, a weighted energy cost model for households within the microgrid (MG) is designed. To address the multisource uncertainty during the operation period, a two-stage stochastic framework is developed. Moreover, to assess the proposed method, the unbalanced IEEE 123 node system is employed and modified as an isolated MG. The analysis reveals the proposed model can achieve a risk-averse solution while economic optimality is guaranteed. Additionally, the designed weighted method improves the LIH’s impact rate to 67.95% and decreases the total planning cost by 22.43%. 

Large language models (LLMs) have achieved impressive performance but face high computational costs and latency, limiting their deployment in resource-constrained settings. In contrast, small-scale LLMs (SLMs) are more efficient yet struggle to capture evolving real-world knowledge. Retrieval-augmented generation (RAG) helps by integrating external knowledge, but imperfect retrieval can introduce distracting noise that misleads SLMs. We propose {\name}, a robust RAG framework for SLMs via Margin-aware Preference Optimization. {\name} employs multi-turn prompting for detailed reasoning, rejection sampling for high-quality explanations, and contrastive preference selection to refine responses by maximizing the likelihood gap between preferred and non-preferred outputs. 

Prior research has highlighted users’ preferences for embodiment when interacting with virtual agents in augmented reality headsets. However, open questions remain regarding users’ preferences towards agent placement and gaze direction. In our study, we asked 48 adults to wear the Microsoft HoloLens 2 and find objects in a hidden object game with the help of embodied agents. We examined four distinct agent configurations for both male and female agents: a human-size agent standing beside participants, a human-size agent sitting beside participants, a small desk agent facing the screen, and a small desk agent facing the participant. Overall, participants preferred male over female virtual agents when receiving assistance, and no consistent preference emerged regarding the agents’ position or gaze direction. From our results, we build upon existing guidelines for designing better virtual agents for AR with headsets. 

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing (KE) to update specific knowledge in LLMs without changing unrelated others or compromising their pre-trained capabilities. Previous efforts sought to update a small amount of parameters of a LLM and proved effective for making selective updates. Nonetheless, the edited LLM often exhibits degraded ability to reason about the new knowledge. In this work, we identify a key issue: \textit{heterogeneous token overfitting} (HTO), where the LLM overfits different tokens in the provided knowledge at varying rates. To tackle this, we propose {\NAME}, a token-level smoothing method that mitigates HTO by adaptively refining the target distribution. Theoretically, {\NAME} offers better parameter updates with negligible computation overhead. It also induces an implicit DPO but does not require preference data pairs. Extensive experiments across four editing methods, two LLMs, and diverse scenarios demonstrate the effectiveness and versatility of our method.