In retrieval augmented generation (RAG) systems, each individual component -- the LLM, embedder, and corpus -- could introduce biases in the form of skews towards outputting certain perspectives or identities. In this work, we study the conflict between biases of each component and their relationship to the overall bias of the RAG system, which we call bias conflict. Examining both gender and political biases as case studies, we show that bias conflict can be characterized through a linear relationship among components despite its complexity in 6 different LLMs. Through comprehensive fine-tuning experiments creating 120 differently biased embedders, we demonstrate how to control bias while maintaining utility and reveal the importance of reverse-biasing the embedder to mitigate bias in the overall system. Additionally, we find that LLMs and tasks exhibit varying sensitivities to the embedder bias, a crucial factor to consider for debiasing. Our results underscore that a fair RAG system can be better achieved by carefully controlling the bias of the embedder rather than increasing its fairness.

--Electric load forecasting is essential for power management and stability in smart grids. This is mainly achieved via advanced metering infrastructure, where smart meters (SMs) record household energy data. Traditional machine learning (ML) methods are often employed for load forecasting but require data sharing which raises data privacy concerns. Federated learning (FL) can address this issue by running distributed ML models at local SMs without data exchange. However, current FL-based approaches struggle to achieve efficient load forecasting due to imbalanced data distribution across heterogeneous SMs. This paper presents a novel personalized federated learning (PFL) method for high-quality load forecasting in metering networks. A meta-learning-based strategy is developed to address data heterogeneity at local SMs in the collaborative training of local load forecasting models. Moreover, to minimize the load forecasting delays in our PFL model, we study a new latency optimization problem based on optimal resource allocation at SMs. A theoretical convergence analysis is also conducted to provide insights into FL design for federated load forecasting. Extensive simulations from real-world datasets show that our method outperforms existing approaches in terms of better load forecasting and reduced operational latency costs. Electrical load forecasting is crucial for power management in smart grids. This service is mainly supported via advanced metering infrastructure, where smart meters (SMs) record household energy consumption and share this data to the server of utility company [2]. This enables utility providers to estimate future electricity demands and thereby bolster grid reliability. Conventional load-forecasting techniques in machine learning (ML) and deep learning (DL) techniques utilize pattern-finding abilities to predict future outcomes.

Long context is an important topic in Natural Language Processing (NLP), running through the development of NLP architectures, and offers immense opportunities for Large Language Models (LLMs) giving LLMs the lifelong learning potential akin to humans. Unfortunately, the pursuit of a long context is accompanied by numerous obstacles. Nevertheless, long context remains a core competitive advantage for LLMs. In the past two years, the context length of LLMs has achieved a breakthrough extension to millions of tokens. Moreover, the research on long-context LLMs has expanded from length extrapolation to a comprehensive focus on architecture, infrastructure, training, and evaluation technologies. Inspired by the symphonic poem, Thus Spake Zarathustra, we draw an analogy between the journey of extending the context of LLM and the attempts of humans to transcend its mortality. In this survey, We will illustrate how LLM struggles between the tremendous need for a longer context and its equal need to accept the fact that it is ultimately finite. To achieve this, we give a global picture of the lifecycle of long-context LLMs from four perspectives: architecture, infrastructure, training, and evaluation, showcasing the full spectrum of long-context technologies. At the end of this survey, we will present 10 unanswered questions currently faced by long-context LLMs. We hope this survey can serve as a systematic introduction to the research on long-context LLMs.

The growing penetration of renewable energy sources in power systems has increased the complexity and uncertainty of load forecasting, especially for integrated energy systems with multiple energy carriers. Traditional forecasting methods heavily rely on historical data and exhibit limited transferability across different scenarios, posing significant challenges for emerging applications in smart grids and energy internet. This paper proposes the TSLLM-Load Forecasting Mechanism, a novel zero-shot load forecasting framework based on large language models (LLMs) to address these challenges. The framework consists of three key components: a data preprocess-ing module that handles multi-source energy load data, a time series prompt generation module that bridges the semantic gap between energy data and LLMs through multi-task learning and similarity alignment, and a prediction module that leverages pre-trained LLMs for accurate forecasting. The framework's effectiveness was validated on a real-world dataset comprising load profiles from 20 Australian solar-powered households, demonstrating In conventional testing, our method achieved a Mean Squared Error (MSE) of 0.4163 and a Mean Absolute Error (MAE) of 0.3760, outperforming existing approaches by at least 8%. In zero-shot prediction experiments across 19 households, the framework maintained consistent accuracy with a total MSE of 11.2712 and MAE of 7.6709, showing at least 12% improvement over current methods. The results validate the framework's potential for accurate and transferable load forecasting in integrated energy systems, particularly beneficial for renewable energy integration and smart grid applications. Keywords: Zero-shot forecasting, Large language models (LLMs), Time series prompt generation, Multi-task learning, Similarity alignment1. Introduction The growing penetration of renewable energy generation has led to significant challenges for power systems, particularly in terms of system dispatch and balance.

Modern fire management systems increasingly rely on satellite data and weather forecasting; however, access to comprehensive datasets remains limited due to proprietary restrictions. Despite the ecological significance of wildfires, large-scale, multi-regional research is constrained by data scarcity. Russian diverse ecosystems play a crucial role in shaping Eurasian fire dynamics, yet they remain underexplored. This study addresses existing gaps by introducing an open-access dataset that captures detailed fire incidents alongside corresponding meteorological conditions. We present one of the most extensive datasets available for wildfire analysis in Russia, covering 13 consecutive months of observations. Leveraging machine learning techniques, we conduct exploratory data analysis and develop predictive models to identify key fire behavior patterns across different fire categories and ecosystems. Our results highlight the critical influence of environmental factor patterns on fire occurrence and spread behavior. By improving the understanding of wildfire dynamics in Eurasia, this work contributes to more effective, data-driven approaches for proactive fire management in the face of evolving environmental conditions.

Motivated by the great success of Bayesian additive regression trees (BART) on regression, we propose a nonparametric Bayesian approach for the function-on-scalar regression problem, termed as Functional BART (FBART). Utilizing spline-based function representation and tree-based domain partition model, FBART offers great flexibility in characterizing the complex and heterogeneous relationship between the response curve and scalar covariates. We devise a tailored Bayesian backfitting algorithm for estimating the parameters in the FBART model. Furthermore, we introduce an FBART model with shape constraints on the response curve, enhancing estimation and prediction performance when prior shape information of response curves is available. By incorporating a shape-constrained prior, we ensure that the posterior samples of the response curve satisfy the required shape constraints (e.g., monotonicity and/or convexity). Our proposed FBART model and its shape-constrained version are the new advances of BART models for functional data. Under certain regularity conditions, we derive the posterior convergence results for both FBART and its shape-constrained version. Finally, the superiority of the proposed methods over other competitive counterparts is validated through simulation experiments under various settings and analyses of two real datasets.

Emergency Response Time (ERT) is crucial for urban safety, measuring cities' ability to handle medical, fire, and crime emergencies. In NYC, medical ERT increased 72% from 7.89 minutes in 2014 to 14.27 minutes in 2024, with half of delays due to Emergency Vehicle (EMV) travel times. Each minute's delay in stroke response costs 2 million brain cells, while cardiac arrest survival drops 7-10% per minute. This dissertation advances EMV facilitation through three contributions. First, EMVLight, a decentralized multi-agent reinforcement learning framework, integrates EMV routing with traffic signal pre-emption. It achieved 42.6% faster EMV travel times and 23.5% improvement for other vehicles. Second, the Dynamic Queue-Jump Lane system uses Multi-Agent Proximal Policy Optimization for coordinated lane-clearing in mixed autonomous and human-driven traffic, reducing EMV travel times by 40%. Third, an equity study of NYC Emergency Medical Services revealed disparities across boroughs: Staten Island faces delays due to sparse signalized intersections, while Manhattan struggles with congestion. Solutions include optimized EMS stations and improved intersection designs. These contributions enhance EMV mobility and emergency service equity, offering insights for policymakers and urban planners to develop safer, more efficient transportation systems.

On Enhancing Structural Resilience of Multirobot Coverage Control with Bearing Rigidity Kartik A. Pant, Vishnu Vijay, Minhyun Cho, and Inseok Hwang Abstract -- The problem of multi-robot coverage control has been widely studied to efficiently coordinate a team of robots to cover a desired area of interest. However, this problem faces significant challenges when some robots are lost or deviate from their desired formation during the mission due to faults or cyberattacks. Since a majority of multi-robot systems (MRSs) rely on communication and relative sensing for their efficient operation, a failure in one robot could result in a cascade of failures in the entire system. In this work, we propose a hierarchical framework for area coverage, combining centralized coordination by leveraging Voronoi partitioning with decentralized reference tracking model predictive control (MPC) for control design. In addition to reference tracking, the decentralized MPC also performs bearing maintenance to enforce a rigid MRS network, thereby enhancing the structural resilience, i.e., the ability to detect and mitigate the effects of localization errors and robot loss during the mission. Furthermore, we show that the resulting control architecture guarantees the recovery of the MRS network in the event of robot loss while maintaining a minimally rigid structure. The effectiveness of the proposed algorithm is validated through numerical simulations. I NTRODUCTION Recent advances in multi-robot systems (MRSs), with their superior sensing, communication, and computational capabilities, allow them to perform complicated tasks otherwise impossible with only single-robot systems. MRSs have been widely adopted for numerous applications such as cooperative sensor coverage [1], search and rescue [2], and environmental monitoring [3]. In recent catastrophic wildfires in Los Angeles, drone swarms have been actively utilized for monitoring and prevention of wildfires [4]. However, as the complexity of these systems increases, the number of failure modes affecting MRS performance and safety also increases. Furthermore, the sensing [5], [6], and communication networks [7] also open up new cyberattack surfaces, network vulnerabilities, and backdoors, which adversaries can exploit to degrade and disrupt the performance of the MRS. Thus, designing control architectures ensuring the system's resiliency under these unknown failure modes becomes essential. A key application of MRSs is to cover a desired area of interest, often denoted by a density function that indicates The authors are with the School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN 47906.

Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-party library APIs. This limitation, stemming from static pre-training datasets, often results in non-executable code or implementations with suboptimal safety and efficiency. To this end, this paper introduces CODESYNC, a data engine for identifying outdated code patterns and collecting real-time code knowledge updates from Python third-party libraries. Building upon CODESYNC, we develop CODESYNCBENCH, a comprehensive benchmark for assessing LLMs' ability to stay synchronized with code evolution, which covers real-world updates for 220 APIs from six Python libraries. Our benchmark offers 3,300 test cases across three evaluation tasks and an update-aware instruction tuning dataset consisting of 2,200 training samples. Extensive experiments on 14 state-of-the-art LLMs reveal that they struggle with dynamic code evolution, even with the support of advanced knowledge updating methods (e.g., DPO, ORPO, and SimPO). We believe that our benchmark can offer a strong foundation for the development of more effective methods for real-time code knowledge updating in the future. The experimental code and dataset are publicly available at: https://github.com/Lucky-voyage/Code-Sync.

Many inference scaling methods work by breaking a problem into smaller steps (or groups of tokens), then sampling and choosing the best next step. However, these steps and their sizes are usually predetermined based on human intuition or domain knowledge. This paper introduces dynamic decomposition, a method that automatically and adaptively splits solution and reasoning traces into steps during inference. This approach improves computational efficiency by focusing more resources on difficult steps, breaking them down further and prioritizing their sampling. Experiments on coding and math benchmarks (APPS, MATH, and LiveCodeBench) show that dynamic decomposition performs better than static methods, which rely on fixed steps like token-level, sentence-level, or single-step decompositions. These results suggest that dynamic decomposition can enhance many inference scaling techniques.