arXiv subjects

Mingyu Guo

Publications and source records attributed to Mingyu Guo.

At least 55 records · Page 3Linked to original sources

arXiv2025

Symmetry-Breaking Augmentations for Ad Hoc Teamwork

In dynamic collaborative settings, for artificial intelligence (AI) agents to better align with humans, they must adapt to novel teammates who utilise unforeseen strategies. While adaptation is often simple for humans, it can be challenging for AI agents. Our work introduces symmetry-breaking augmentations (SBA) as a novel approach to this challenge. By applying a symmetry-flipping operation to increase behavioural diversity among training teammates, SBA encourages agents to learn robust responses to unknown strategies, highlighting how social conventions impact human-AI alignment. We demonstrate this experimentally in two settings, showing that our approach outperforms previous ad hoc teamwork results in the challenging card game Hanabi. In addition, we propose a general metric for estimating symmetry dependency amongst a given set of policies. Our findings provide insights into how AI systems can better adapt to diverse human conventions and the core mechanics of alignment.

cs.LG↗

arXiv2025

Parameter constraints on a black hole with Minkowski core through quasiperiodic oscillations

We investigate the geodesic motion of charged particles in the vicinity of regular black holes with a Minkowski core, embedded in a uniform magnetic field, and study the influences of magnetic field and regular black hole parameter on the radial effective potential and angular momentum of the particles' orbits. We perturb the circular orbit and analyze the characteristic frequencies of the epicyclic oscillations, which are closely related with the quasiperiodic oscillations (QPOs) phenomena of the accretion disc surrounding the black hole. Then using the MCMC simulation, we fit our theoretical results with four observational QPOs events (GRO J1655-40, XTE J1550-564, XTE J1859+226, and GRS 1915+105) and provide constraints on the magnetic field strength $B$, the characteristic radius $r$, the mass $M$, and the regular black hole parameter $g$. In particular, since the parameter $g$ describes the degree of deviation from the classical Schwarzschild black hole, our studies suggest that, within a certain level of confidence, the black holes in the current model can deviate from the classical singularity structure of Schwarzschild black holes, and exhibit quantum corrections near the core.

gr-qc↗

arXiv2025

EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

Recent advancements in video generation have significantly impacted various downstream applications, particularly in identity-preserving video generation (IPT2V). However, existing methods struggle with "copy-paste" artifacts and low similarity issues, primarily due to their reliance on low-level facial image information. This dependence can result in rigid facial appearances and artifacts reflecting irrelevant details. To address these challenges, we propose EchoVideo, which employs two key strategies: (1) an Identity Image-Text Fusion Module (IITF) that integrates high-level semantic features from text, capturing clean facial identity representations while discarding occlusions, poses, and lighting variations to avoid the introduction of artifacts; (2) a two-stage training strategy, incorporating a stochastic method in the second phase to randomly utilize shallow facial information. The objective is to balance the enhancements in fidelity provided by shallow features while mitigating excessive reliance on them. This strategy encourages the model to utilize high-level features during training, ultimately fostering a more robust representation of facial identities. EchoVideo effectively preserves facial identities and maintains full-body integrity. Extensive experiments demonstrate that it achieves excellent results in generating high-quality, controllability and fidelity videos.

cs.CV↗

arXiv2025

Discovering Structural Hole Spanners in Dynamic Networks via Graph Neural Networks

Structural Hole (SH) theory states that the node which acts as a connecting link among otherwise disconnected communities gets positional advantages in the network. These nodes are called Structural Hole Spanners (SHS). SHSs have many applications, including viral marketing, information dissemination, community detection, etc. Numerous solutions are proposed to discover SHSs; however, most of the solutions are only applicable to static networks. Since real-world networks are dynamic networks; consequently, in this study, we aim to discover SHSs in dynamic networks. Discovering SHSs is an NP-hard problem, due to which, instead of discovering exact k SHSs, we adopt a greedy approach to discover top-k SHSs. Motivated from the success of Graph Neural Networks (GNNs) on various graph mining problems, we design a Graph Neural Network-based model, GNN-SHS, to discover SHSs in dynamic networks, aiming to reduce the computational cost while achieving high accuracy. We analyze the efficiency of the proposed model through exhaustive experiments, and our results show that the proposed GNN-SHS model is at least 31.8 times faster and, on an average 671.6 times faster than the comparative method, providing a considerable efficiency advantage.

cs.SI↗

arXiv2025

Effective Graph-Neural-Network based Models for Discovering Structural Hole Spanners in Large-Scale and Diverse Networks

A Structural Hole Spanner (SHS) is a set of nodes in a network that act as a bridge among different otherwise disconnected communities. Numerous solutions have been proposed to discover SHSs that generally require high run time on large-scale networks. Another challenge is discovering SHSs across different types of networks for which the traditional one-model-fit-all approach fails to capture the inter-graph difference, particularly in the case of diverse networks. Therefore, there is an urgent need of developing effective solutions for discovering SHSs in large-scale and diverse networks. Inspired by the recent advancement of graph neural network approaches on various graph problems, we propose graph neural network-based models to discover SHS nodes in large scale networks and diverse networks. We transform the problem into a learning problem and propose an efficient model GraphSHS, that exploits both the network structure and node features to discover SHS nodes in large scale networks, endeavouring to lessen the computational cost while maintaining high accuracy. To effectively discover SHSs across diverse networks, we propose another model Meta-GraphSHS based on meta-learning that learns generalizable knowledge from diverse training graphs (instead of directly learning the model) and utilizes the learned knowledge to create a customized model to identify SHSs in each new graph. We theoretically show that the depth of the proposed graph neural network model should be at least $Ω(\sqrt{n}/\log n)$ to accurately calculate the SHSs discovery problem. We evaluate the performance of the proposed models through extensive experiments on synthetic and real-world datasets. Our experimental results show that GraphSHS discovers SHSs with high accuracy and is at least 167.1 times faster than the comparative methods on large-scale real-world datasets.

cs.SI↗

arXiv2025

Maintenance of Structural Hole Spanners in Dynamic Networks

Structural Hole (SH) spanners are the set of users who bridge different groups of users and are vital in numerous applications. Despite their importance, existing work for identifying SH spanners focuses only on static networks. However, real-world networks are highly dynamic where the underlying structure of the network evolves continuously. Consequently, we study SH spanner problem for dynamic networks. We propose an efficient solution for updating SH spanners in dynamic networks. Our solution reuses the information obtained during the initial runs of the static algorithm and avoids the recomputations for the nodes unaffected by the updates. Experimental results show that the proposed solution achieves a minimum speedup of 3.24 over recomputation. To the best of our knowledge, this is the first attempt to address the problem of maintaining SH spanners in dynamic networks.

cs.SI↗

arXiv2025

An Interpretable Automated Mechanism Design Framework with Large Language Models

Mechanism design has long been a cornerstone of economic theory, with traditional approaches relying on mathematical derivations. Recently, automated approaches, including differentiable economics with neural networks, have emerged for designing payments and allocations. While both analytical and automated methods have advanced the field, they each face significant weaknesses: mathematical derivations are not automated and often struggle to scale to complex problems, while automated and especially neural-network-based approaches suffer from limited interpretability. To address these challenges, we introduce a novel framework that reformulates mechanism design as a code generation task. Using large language models (LLMs), we generate heuristic mechanisms described in code and evolve them to optimize over some evaluation metrics while ensuring key design criteria (e.g., strategy-proofness) through a problem-specific fixing process. This fixing process ensures any mechanism violating the design criteria is adjusted to satisfy them, albeit with some trade-offs in performance metrics. These trade-offs are factored in during the LLM-based evolution process. The code generation capabilities of LLMs enable the discovery of novel and interpretable solutions, bridging the symbolic logic of mechanism design and the generative power of modern AI. Through rigorous experimentation, we demonstrate that LLM-generated mechanisms achieve competitive performance while offering greater interpretability compared to previous approaches. Notably, our framework can rediscover existing manually designed mechanisms and provide insights into neural-network based solutions through Programming-by-Example. These results highlight the potential of LLMs to not only automate but also enhance the transparency and scalability of mechanism design, ensuring safe deployment of the mechanisms in society.

cs.LG↗

arXiv2025

CascadeV: An Implementation of Wurstchen Architecture for Video Generation

Recently, with the tremendous success of diffusion models in the field of text-to-image (T2I) generation, increasing attention has been directed toward their potential in text-to-video (T2V) applications. However, the computational demands of diffusion models pose significant challenges, particularly in generating high-resolution videos with high frame rates. In this paper, we propose CascadeV, a cascaded latent diffusion model (LDM), that is capable of producing state-of-the-art 2K resolution videos. Experiments demonstrate that our cascaded model achieves a higher compression ratio, substantially reducing the computational challenges associated with high-quality video generation. We also implement a spatiotemporal alternating grid 3D attention mechanism, which effectively integrates spatial and temporal information, ensuring superior consistency across the generated video frames. Furthermore, our model can be cascaded with existing T2V models, theoretically enabling a 4$\times$ increase in resolution or frames per second without any fine-tuning. Our code is available at https://github.com/bytedance/CascadeV.

cs.CV↗

arXiv2025

Strong gravitational lensing effects around rotating regular black holes

In this letter, we investigate the strong gravitational lensing effects around two classes of rotating regular black holes, which behave as non-singular Minkowski core at the center. Starting from the null geodesic in the equatorial plane of the regular black holes, we analyze the deflection angle for both prograde photons and retrograde photons, which are found to significantly shift from that for Kerr black hole. Then we suppose the rotating regular black holes as the supermassive M87* and SgrA* black holes, respectively, and evaluate the lensing observables such as the image position, separation, magnification and the time delays between the relativistic images for the black holes. In both cases, the time delay differences between the regular black holes and Kerr black hole seem to be measurable, especially for the M87* black hole, but the deviations of outermost relativistic image and the asymptotic relativistic image for the two rotating regular black holes from those for Kerr black hole are less than 10 $μas$. This means that it is difficult to probe the regularity of the black hole via the current observations, but we can expect the next generation Event Horizon Telescope to test more precise properties of strong field regime.

gr-qc↗

arXiv2024

Discovering Top-k Structural Hole Spanners in Dynamic Networks

Structural Hole (SH) theory states that the node which acts as a connecting link among otherwise disconnected communities gets positional advantages in the network. These nodes are called Structural Hole Spanners (SHS). Numerous solutions are proposed to discover SHSs; however, most of the solutions are only applicable to static networks. Since real-world networks are dynamic networks; consequently, in this study, we aim to discover SHSs in dynamic networks. Discovering SHSs is an NP-hard problem, due to which, instead of discovering exact k SHSs, we adopt a greedy approach to discover Top-k SHSs. We first propose an efficient Tracking-SHS algorithm for updating SHSs in dynamic networks. Our algorithm reuses the information obtained during the initial runs of the static algorithm and avoids the recomputations for the nodes unaffected by the updates. Besides, motivated from the success of Graph Neural Networks (GNNs) on various graph mining problems, we also design a Graph Neural Network-based model, GNN-SHS, to discover SHSs in dynamic networks, aiming to reduce the computational cost while achieving high accuracy. We provide a theoretical analysis of the Tracking-SHS algorithm, and our theoretical results prove that for a particular type of graphs, such as Preferential Attachment graphs [1], Tracking-SHS algorithm achieves 1.6 times of speedup compared with the static algorithm. We perform extensive experiments, and our results demonstrate that the Tracking-SHS algorithm attains a minimum of 3.24 times speedup over the static algorithm. Also, the proposed second model GNN-SHS is on an average 671.6 times faster than the Tracking-SHS algorithm.

cs.SI↗

arXiv2024

A Pre-trained Deep Potential Model for Sulfide Solid Electrolytes with Broad Coverage and High Accuracy

Solid electrolytes with fast ion transport are one of the key challenges for solid state lithium metal batteries. To improve ion conductivity, chemical doping has been the most effective strategy, and atomistic simulation with machine-learning potential helps find optimized doping by predicting ion conductivity for arbitrary composition. Yet most existing machine-learning models are trained on narrow chemistry, and new model has to be trained for each system, wasting transferable knowledge and incurring significant cost. Here, we propose a pre-trained deep potential model purpose-built for sulfide electrolytes with attention mechanism, known as DPA-SSE. The training set encompasses 15 elements and consists of both equilibrium and extensive out-of-equilibrium configurations. DPA-SSE achieves a high energy resolution of less than 2 meV/atom for dynamical trajectories up to 1150 K, and reproduces experimental ion conductivity of sulfide electrolytes with remarkable accuracy. DPA-SSE exhibits good transferability, covering a range of complex electrolytes with mixes of cation and anion atoms. Highly efficient dynamical simulation with DPA-SSE can be realized by model distillation which generates a faster model for given systems. DPA-SSE also serves as a platform for continuous learning, and the model fine-tune requires only a portion of downstream data. These results demonstrate the possibility of a new pathway for AI-driven development of solid electrolytes with exceptional performance.

physics.chem-ph↗

arXiv2024

Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning

This paper addresses a significant gap in Autonomous Cyber Operations (ACO) literature: the absence of effective edge-blocking ACO strategies in dynamic, real-world networks. It specifically targets the cybersecurity vulnerabilities of organizational Active Directory (AD) systems. Unlike the existing literature on edge-blocking defenses which considers AD systems as static entities, our study counters this by recognizing their dynamic nature and developing advanced edge-blocking defenses through a Stackelberg game model between attacker and defender. We devise a Reinforcement Learning (RL)-based attack strategy and an RL-assisted Evolutionary Diversity Optimization-based defense strategy, where the attacker and defender improve each other strategy via parallel gameplay. To address the computational challenges of training attacker-defender strategies on numerous dynamic AD graphs, we propose an RL Training Facilitator that prunes environments and neural networks to eliminate irrelevant elements, enabling efficient and scalable training for large graphs. We extensively train the attacker strategy, as a sophisticated attacker model is essential for a robust defense. Our empirical results successfully demonstrate that our proposed approach enhances defender's proficiency in hardening dynamic AD graphs while ensuring scalability for large-scale AD.

cs.CR↗

arXiv2024

Disentangling Specificity for Abstractive Multi-document Summarization

Multi-document summarization (MDS) generates a summary from a document set. Each document in a set describes topic-relevant concepts, while per document also has its unique contents. However, the document specificity receives little attention from existing MDS approaches. Neglecting specific information for each document limits the comprehensiveness of the generated summaries. To solve this problem, in this paper, we propose to disentangle the specific content from documents in one document set. The document-specific representations, which are encouraged to be distant from each other via a proposed orthogonal constraint, are learned by the specific representation learner. We provide extensive analysis and have interesting findings that specific information and document set representations contribute distinctive strengths and their combination yields a more comprehensive solution for the MDS. Also, we find that the common (i.e. shared) information could not contribute much to the overall performance under the MDS settings. Implemetation codes are available at https://github.com/congboma/DisentangleSum.

cs.IR↗

arXiv2024

Optimizing Cyber Response Time on Temporal Active Directory Networks Using Decoys

Microsoft Active Directory (AD) is the default security management system for Window domain network. We study the problem of placing decoys in AD network to detect potential attacks. We model the problem as a Stackelberg game between an attacker and a defender on AD attack graphs where the defender employs a set of decoys to detect the attacker on their way to Domain Admin (DA). Contrary to previous works, we consider time-varying (temporal) attack graphs. We proposed a novel metric called response time, to measure the effectiveness of our decoy placement in temporal attack graphs. Response time is defined as the duration from the moment attackers trigger the first decoy to when they compromise the DA. Our goal is to maximize the defender's response time to the worst-case attack paths. We establish the NP-hard nature of the defender's optimization problem, leading us to develop Evolutionary Diversity Optimization (EDO) algorithms. EDO algorithms identify diverse sets of high-quality solutions for the optimization problem. Despite the polynomial nature of the fitness function, it proves experimentally slow for larger graphs. To enhance scalability, we proposed an algorithm that exploits the static nature of AD infrastructure in the temporal setting. Then, we introduce tailored repair operations, ensuring the convergence to better results while maintaining scalability for larger graphs.

cs.CR↗

arXiv2024

Modelling Irrational Behaviour of Residential End Users using Non-Stationary Gaussian Processes

Demand response (DR) plays a critical role in ensuring efficient electricity consumption and optimal use of network assets. Yet, existing DR models often overlook a crucial element, the irrational behaviour of electricity end users. In this work, we propose a price-responsive model that incorporates key aspects of end-user irrationality, specifically loss aversion, time inconsistency, and bounded rationality. To this end, we first develop a framework that uses Multiple Seasonal-Trend decomposition using Loess (MSTL) and non-stationary Gaussian processes to model the randomness in the electricity consumption by residential consumers. The impact of this model is then evaluated through a community battery storage (CBS) business model. Additionally, we apply a chance-constrained optimisation model for CBS operation that deals with the unpredictability of the end-user irrationality. Our simulations using real-world data show that the proposed DR model provides a more realistic estimate of end-user price-responsive behaviour when considering irrationality. Compared to a deterministic model that cannot fully take into account the irrational behaviour of end users, the chance-constrained CBS operation model yields an additional 19% revenue. Lastly, the business model reduces the electricity costs of solar end users by 11%.

eess.SY↗

arXiv2024

Evolutionary Multi-Objective Diversity Optimization

Creating diverse sets of high quality solutions has become an important problem in recent years. Previous works on diverse solutions problems consider solutions' objective quality and diversity where one is regarded as the optimization goal and the other as the constraint. In this paper, we treat this problem as a bi-objective optimization problem, which is to obtain a range of quality-diversity trade-offs. To address this problem, we frame the evolutionary process as evolving a population of populations, and present a suitable general implementation scheme that is compatible with existing evolutionary multi-objective search methods. We realize the scheme in NSGA-II and SPEA2, and test the methods on various instances of maximum coverage, maximum cut and minimum vertex cover problems. The resulting non-dominated populations exhibit rich qualitative features, giving insights into the optimization instances and the quality-diversity trade-offs they induce.

cs.NE↗

arXiv2023

Catch Me if You Can: Effective Honeypot Placement in Dynamic AD Attack Graphs

We study a Stackelberg game between an attacker and a defender on large Active Directory (AD) attack graphs where the defender employs a set of honeypots to stop the attacker from reaching high-value targets. Contrary to existing works that focus on small and static attack graphs, AD graphs typically contain hundreds of thousands of nodes and edges and constantly change over time. We consider two types of attackers: a simple attacker who cannot observe honeypots and a competent attacker who can. To jointly solve the game, we propose a mixed-integer programming (MIP) formulation. We observed that the optimal blocking plan for static graphs performs poorly in dynamic graphs. To solve the dynamic graph problem, we re-design the mixed-integer programming formulation by combining m MIP (dyMIP(m)) instances to produce a near-optimal blocking plan. Furthermore, to handle a large number of dynamic graph instances, we use a clustering algorithm to efficiently find the m-most representative graph instances for a constant m (dyMIP(m)). We prove a lower bound on the optimal blocking strategy for dynamic graphs and show that our dyMIP(m) algorithms produce close to optimal results for a range of AD graphs under realistic conditions.

cs.AI↗

arXiv2023

Limited Query Graph Connectivity Test

We propose a combinatorial optimisation model called Limited Query Graph Connectivity Test. We consider a graph whose edges have two possible states (On/Off). The edges' states are hidden initially. We could query an edge to reveal its state. Given a source s and a destination t, we aim to test s-t connectivity by identifying either a path (consisting of only On edges) or a cut (consisting of only Off edges). We are limited to B queries, after which we stop regardless of whether graph connectivity is established. We aim to design a query policy that minimizes the expected number of queries. Our model is mainly motivated by a cyber security use case where we need to establish whether an attack path exists in a network, between a source and a destination. Edge query is resolved by manual effort from the IT admin, which is the motivation behind query minimization. Our model is highly related to monotone Stochastic Boolean Function Evaluation (SBFE). There are two existing exact algorithms for SBFE that are prohibitively expensive. We propose a significantly more scalable exact algorithm. While previous exact algorithms only scale for trivial graphs (i.e., past works experimented on at most 20 edges), we empirically demonstrate that our algorithm is scalable for a wide range of much larger practical graphs (i.e., Windows domain network graphs with tens of thousands of edges). We propose three heuristics. Our best-performing heuristic is via reducing the search horizon of the exact algorithm. The other two are via reinforcement learning (RL) and Monte Carlo tree search (MCTS). We also derive an anytime algorithm for computing the performance lower bound. Experimentally, we show that all our heuristics are near optimal. The exact algorithm based heuristic outperforms all, surpassing RL, MCTS and 8 existing heuristics ported from SBFE and related literature.

cs.DS↗