Jiankang Wang

Daijiafan Mao, Jun Tan, Guangyi Liu et al.

Under the ambition of boosting Plug-in Electric Vehicle (PEV) charging speed to a level comparable to the traditional refueling, Fast Charging Station (FCS) has been integrated into power distribution system. The location planning of FCS must allow for satisfactory charging service for PEV users as well as mitigate the detrimental effects on power grid caused by uncertainty and impulsiveness of charging demand. This paper proposed a location planning model for FCS, taking into account its impacts on the critical power grid assets. The multi-objective planning model simultaneously considered the role of FCS in the electricity and transportation sectors. This planning model is solved by the cross-entropy (CE) method. The validity and effectiveness of the CE approach have been demonstrated on a synthetic coupled network.

Daijiafan Mao, Ziran Gao, Jiankang Wang

Plug-in Electric Vehicles (PEV) exert an increasingly disruptive influence on power delivery systems with penetration surge in the past decade. Therefore, accurately assessing their impact plays a crucial role in managing grid assets and maintaining power grids reliability. However, PEV loads are stochastic and impulsive, which means they are of high power density and vary in a fast and discrete manner. These load characteristics make conventional assessment methods unsuitable. This paper proposes an algorithm, which captures the inter-temporal response of grid assets and allows fast assessment through an integrated interface. To realize these advantageous features, we establish analytical models for two generic classes of grid assets (continuous and discrete operating assets) and recast their cost functions in the statistical settings of PEV charging. Distinct from simulation-based methods, the proposed method is analytical, and thus greatly reduce the computation resources and data required for accurate assessment. The effectiveness of the proposed algorithm has been demonstrated on a set of power distribution networks in Columbus metropolitan area, in comparison with the conventional assessment methods.

Zhongwei Yu, Rasul Tutunov, Alexandre Max Maraval et al.

Traditional scientific discovery relies on an iterative hypothesise-experiment-refine cycle that has driven progress for centuries, but its intuitive, ad-hoc implementation often wastes resources, yields inefficient designs, and misses critical insights. This tutorial presents Bayesian Optimisation (BO), a principled probability-driven framework that formalises and automates this core scientific cycle. BO uses surrogate models (e.g., Gaussian processes) to model empirical observations as evolving hypotheses, and acquisition functions to guide experiment selection, balancing exploitation of known knowledge and exploration of uncharted domains to eliminate guesswork and manual trial-and-error. We first frame scientific discovery as an optimisation problem, then unpack BO's core components, end-to-end workflows, and real-world efficacy via case studies in catalysis, materials science, organic synthesis, and molecule discovery. We also cover critical technical extensions for scientific applications, including batched experimentation, heteroscedasticity, contextual optimisation, and human-in-the-loop integration. Tailored for a broad audience, this tutorial bridges AI advances in BO with practical natural science applications, offering tiered content to empower cross-disciplinary researchers to design more efficient experiments and accelerate principled scientific discovery.

Jiankang Wang, Zhihan Zhang, Zhihang Liu et al.

Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly, it is difficult to extract accurate spatio-temporal information of each frame in the video. Secondly, the substantial number of visual tokens makes it challenging to precisely map visual tokens of each frame to their corresponding spatial coordinates. To address these issues, we introduce SpaceVLLM, a MLLM endowed with spatio-temporal video grounding capability. Specifically, we adopt a set of interleaved Spatio-Temporal Aware Queries to capture temporal perception and dynamic spatial information. Moreover, we propose a Query-Guided Space Decoder to establish a corresponding connection between the queries and spatial coordinates. Additionally, due to the lack of spatio-temporal datasets, we construct the Unified Spatio-Temporal Grounding (Uni-STG) dataset, comprising 480K instances across three tasks. This dataset fully exploits the potential of MLLM to simultaneously facilitate localization in both temporal and spatial dimensions. Extensive experiments demonstrate that SpaceVLLM achieves the state-of-the-art performance across 11 benchmarks covering temporal, spatial, spatio-temporal and video understanding tasks, highlighting the effectiveness of our approach. Our code, datasets and model will be released at https://github.com/Jayce1kk/SpaceVLLM.

Christian Moya, Jiankang Wang

Increasing reliance on Information and Communication Technology~(ICT) exposes the power grid to cyber-attacks. In particular, Coordinated Cyber-Attacks (CCAs) are considered highly threatening and difficult to defend against, because they (i) possess higher disruptiveness by integrating greater resources from multiple attack entities, and (ii) present heterogeneous traits in cyber-space and the physical grid by hitting multiple targets to achieve the attack goal. Thus, and as opposed to independent attacks, whose severity is limited by the power grid's redundancy, CCAs could inflict disastrous consequences, such as blackouts. In this paper, we propose a method to develop Correlation Indices to defend against CCAs on static control applications. These proposed indices relate the targets of CCAs with attack goals on the power grid. Compared to related works, the proposed indices present the benefits of deployment simplicity and are capable of detecting more sophisticated attacks, such as measurement attacks. We demonstrate our method using measurement attacks against Security Constrained Economic Dispatch.

Jiankang Wang, Jianjun Xu, Xiaorui Wang et al.

Large-scale, high-quality data is essential for advancing the reasoning capabilities of large language models (LLMs). As publicly available Internet data becomes increasingly scarce, synthetic data has emerged as a crucial research direction. However, existing data synthesis methods often suffer from limited scalability, insufficient sample diversity, and a tendency to overfit to seed data, which constrains their practical utility. In this paper, we present \textit{\textbf{GRIP}}, a \textbf{G}raph-based \textbf{R}easoning \textbf{I}nstruction \textbf{P}roducer that efficiently synthesizes high-quality and diverse reasoning instructions. \textit{GRIP} constructs a knowledge graph by extracting high-level concepts from seed data, and uniquely leverages both explicit and implicit relationships within the graph to drive large-scale and diverse instruction data synthesis, while employing open-source multi-model supervision to ensure data quality. We apply \textit{GRIP} to the critical and challenging domain of mathematical reasoning. Starting from a seed set of 7.5K math reasoning samples, we construct \textbf{GRIP-MATH}, a dataset containing 2.1 million synthesized question-answer pairs. Compared to similar synthetic data methods, \textit{GRIP} achieves greater scalability and diversity while also significantly reducing costs. On mathematical reasoning benchmarks, models trained with GRIP-MATH demonstrate substantial improvements over their base models and significantly outperform previous data synthesis methods.

Bowei Pu, Chuanbin Liu, Yifan Ge et al.

Sufficient visual perception is the foundation of video reasoning. Nevertheless, existing Video Reasoning LLMs suffer from perception shortcuts, relying on a flawed single-step perception paradigm. This paradigm describes the video and then conducts reasoning, which runs the risk of insufficient evidence and emergent hallucinations. To address these issues, we introduce a new framework that integrates a loop-based paradigm with an anti-hallucination reward. First, to address the insufficient evidence, we introduce the Perception Loop Reasoning (PLR) paradigm. Instead of describing the video at once, each loop requires the model to describe a video segment with precise timestamps, analyze this segment, and decide the next action. Second, for the risk of hallucinations, the Factual-Aware Evaluator (FAE) evaluates each perception result as a reliable anti-hallucination reward. This reward encourages the model to provide sufficient and precise video evidence. Our FAE, which performs comparably to GPT-4o, is tuned on our AnetHallu-117K, a large-scale hallucination judgment preference dataset. Extensive experiments show that our Video-PLR achieves the state-of-the-art in both 3B and 7B parameter scales and has the best data efficiency. Our code, models, and datasets are released on: https://github.com/BoweiPu/VideoPLR.

Christian Moya, Junho Hong, Jiankang Wang

The future power grid will be characterized by the pervasive use of heterogeneous and non-proprietary information and communication technology, which exposes the power grid to a broad scope of cyber-attacks. In particular, Monitoring-Control Attacks (MCA) --i.e., attacks in which adversaries manipulate control decisions by fabricating measurement signals in the feedback loop-- are highly threatening. This is because, MCAs are (i) more likely to happen with greater attack surface and lower cost, (ii) difficult to detect by hiding in measurement signals, and (iii) capable of inflicting severe consequences by coordinating attack resources. To defend against MCAs, we have developed a semantic analysis framework for Intrusion Detection Systems (IDS) in power grids. The framework consists of two parts running in parallel: a Correlation Index Generator (CIG), which indexes correlated MCAs, and a Correlation Knowledge-Base~(CKB), which is updated aperiodically with attacks' Correlation Indices (CI). The framework has the advantage of detecting MCAs and estimating attack consequences with promising runtime and detection accuracy. To evaluate the performance of the framework, we computed its false alarm rates under different attack scenarios.