arXiv subjects

Bingqing Liu

Publications and source records attributed to Bingqing Liu.

12 recordsLinked to original sources

arXiv2026

GeoMag: Geometric-Aware Video Motion Magnification via State Space Model

Video Motion Magnification (VMM) reveals imperceptible dynamics but often suffers from structural inconsistencies under complex geometric transformations. Existing learning-based methods generally face a trade-off between the limited global context of CNNs and the high computational cost of Transformers. In addition, current training protocols, largely dominated by simple linear motion, fail to capture the geometric and imaging complexities encountered in real-world videos. To address these issues, we propose GeoMag, a geometric-aware VMM framework built upon State Space Models to achieve globally consistent motion amplification with linear complexity. We further construct Geo-200K, a large-scale synthetic dataset that introduces rich geometric transformations together with sensor-realistic degradations, improving the diversity and realism of training signals. Extensive experiments on synthetic and real-world benchmarks show that GeoMag consistently outperforms prior methods in visual fidelity and computational efficiency, while producing fewer artifacts and better structural consistency.

cs.CV↗

arXiv2026

BetaEdit: Null-Space Constrained Sequential Model Editing

Null-space-based methods have garnered considerable attention in model editing by constraining updates to the null space of the pre-existing knowledge representation, thereby preserving the model's original behavior. However, in practice these methods rely on an approximate null space--leading to knowledge leakage--and further suffer from severe performance degradation during sequential editing. Recent work shows that history-aware editing strategies can empirically mitigate this decline, yet the underlying reason remains unclear. In this paper, we first expose the knowledge leakage inherent in existing null-space approaches and then analyze why history-aware updates effectively preserve both editing performance and general capabilities during long-horizon editing. Building on these insights, we propose BetaEdit, a refined framework that effectively controls the knowledge leakage and integrates history-aware updates into the null-space paradigm. Extensive experiments on three large language models across two standard benchmarks show that BetaEdit consistently outperforms prior methods in the challenging regime of massive-scale sequential editing. Code is available at: https://github.com/lbq8942/BetaEdit.

cs.CL↗

arXiv2025

Stochastic assignment games for Mobility-as-a-Service markets

We study the stochastic assignment game and extend it to model multimodal mobility markets with a regulator or a Mobility-as-a-Service (MaaS) platform. We start by presenting general forms of one-to-one and many-to-many stochastic assignment games. Optimality conditions are discussed. The core of stochastic assignment games is defined, with expected payoffs of sellers and buyers in stochastic assignment games as payoffs from a hypothetical "ideal matching" that represent sellers' and buyers' expectations under imperfect information. To apply stochastic assignment games to the urban mobility markets, we extend the general stochastic many-to-many assignment game into a stochastic Stackelberg game to model MaaS systems, where the platform is the leader, and users and operators are the followers. The platform sets fares to maximize revenue. Users and operator react to the fare settings to form a stochastic many-to-many assignment game considering both fixed-route services and Mobility-on-Demand (MOD). The Stackelberg game is formulated as a bilevel problem. The lower level is the stochastic many-to-many assignment game between users and operators, shown to yield a coalitional logit model. The upper-level problem is a fare adjustment problem maximizing revenue. An iterative balancing algorithm is proposed to solve the lower-level problem exactly. The bilevel problem is solved through an iterative fare adjusting heuristic, whose solution is shown to be equivalent to the bilevel problem with an additional condition when it converges. Two case studies are conducted. The model can be applied to design MaaS fares maximizing income of the platform while anticipating the selfish behavior and heterogeneity of users and operators. Public agencies can also use the model to manage multimodal transportation systems.

cs.GT↗

arXiv2025

Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundation

Large language models (LLMs) inevitably encode outdated or incorrect knowledge. Updating, deleting, and forgetting such knowledge is important for alignment, safety, and other issues. To address this issue, model editing has emerged as a promising paradigm: by precisely editing a small subset of parameters such that a specific fact is updated while preserving other knowledge. Despite its great success reported in previous papers, we find the apparent reliability of editing rests on a fragile foundation and the current literature is largely driven by illusory success. The fundamental goal of steering the model's output toward a target with minimal modification would encourage exploiting hidden shortcuts, rather than utilizing real semantics. This problem directly challenges the feasibility of the current model editing literature at its very foundation, as shortcuts are inherently at odds with robust knowledge integration. Coincidentally, this issue has long been obscured by evaluation frameworks that lack the design of negative examples. To uncover it, we systematically develop a suite of new evaluation methods. Strikingly, we find that state-of-the-art approaches collapse even under the simplest negation queries. Our empirical evidence shows that editing is likely to be based on shortcuts rather than full semantics, calling for an urgent reconsideration of the very basis of model editing before further advancements can be meaningfully pursued.

cs.AI↗

arXiv2025

Variational Autoencoder Framework for Hyperspectral Retrievals (Hyper-VAE) of Phytoplankton Absorption and Chlorophyll a in Coastal Waters for NASA's EMIT and PACE Missions

Phytoplankton absorb and scatter light in unique ways, subtly altering the color of water, changes that are often minor for human eyes to detect but can be captured by sensitive ocean color instruments onboard satellites from space. Hyperspectral sensors, paired with advanced algorithms, are expected to significantly enhance the characterization of phytoplankton community composition, especially in coastal waters where ocean color remote sensing applications have historically encountered significant challenges. This study presents novel machine learning-based solutions for NASA's hyperspectral missions, including EMIT and PACE, tackling high-fidelity retrievals of phytoplankton absorption coefficient and chlorophyll a from their hyperspectral remote sensing reflectance. Given that a single Rrs spectrum may correspond to varied combinations of inherent optical properties and associated concentrations, the Variational Autoencoder (VAE) is used as a backbone in this study to handle such multi-distribution prediction problems. We first time tailor the VAE model with innovative designs to achieve hyperspectral retrievals of aphy and of Chl-a from hyperspectral Rrs in optically complex estuarine-coastal waters. Validation with extensive experimental observation demonstrates superior performance of the VAE models with high precision and low bias. The in-depth analysis of VAE's advanced model structures and learning designs highlights the improvement and advantages of VAE-based solutions over the mixture density network (MDN) approach, particularly on high-dimensional data, such as PACE. Our study provides strong evidence that current EMIT and PACE hyperspectral data as well as the upcoming Surface Biology Geology mission will open new pathways toward a better understanding of phytoplankton community dynamics in aquatic ecosystems when integrated with AI technologies.

cs.LG↗

arXiv2024

2FA Sketch: Two-Factor Armor Sketch for Accurate and Efficient Heavy Hitter Detection in Data Streams

Detecting heavy hitters, which are flows exceeding a specified threshold, is crucial for network measurement, but it faces challenges due to increasing throughput and memory constraints. Existing sketch-based solutions, particularly those using Comparative Counter Voting, have limitations in efficiently identifying heavy hitters. This paper introduces the Two-Factor Armor (2FA) Sketch, a novel data structure designed to enhance heavy hitter detection in data streams. 2FA Sketch implements dual-layer protection through an improved $\mathtt{Arbitration}$ strategy for in-bucket competition and a cross-bucket conflict $\mathtt{Avoidance}$ hashing scheme. By theoretically deriving an optimal $λ$ parameter and redesigning $vote^+_{new}$ as a conflict indicator, it optimizes the Comparative Counter Voting strategy. Experimental results show that 2FA Sketch outperforms the standard Elastic Sketch, reducing error rates by 2.5 to 19.7 times and increasing processing speed by 1.03 times.

cs.NI↗

arXiv2024

On-demand Mobility-as-a-Service platform assignment games with guaranteed stable outcomes

Mobility-as-a-Service (MaaS) systems are two-sided markets, with two mutually exclusive sets of agents, i.e., travelers/users and operators, forming a mobility ecosystem in which multiple operators compete or cooperate to serve customers under a governing platform provider. This study proposes a MaaS platform equilibrium model based on many-to-many assignment games incorporating both fixed-route transit services and mobility-on-demand (MOD) services. The matching problem is formulated as a convex multicommodity flow network design problem under congestion that captures the cost of accessing MOD services. The local stability conditions reflect a generalization of Wardrop's principles that include operators' decisions. Due to the presence of congestion, the problem may result in non-stable designs, and a subsidy mechanism from the platform is proposed to guarantee local stability. A new exact solution algorithm to the matching problem is proposed based on a branch and bound framework with a Frank-Wolfe algorithm integrated with Lagrangian relaxation and subgradient optimization, which guarantees the optimality of the matching problem but not stability. A heuristic which integrates stability conditions and subsidy design is proposed, which reaches either an optimal MaaS platform equilibrium solution with global stability, or a feasible locally stable solution that may require subsidy. For the heuristic, a worst-case bound and condition for obtaining an exact solution are both identified. An expanded Sioux Falls network test with 82 nodes and 748 links derives generalizable insights about the model for coopetitive interdependencies between operators sharing the platform, handling congestion effects in MOD services, effects of local stability on investment impacts, and illustrating inequities that may arise under heterogeneous populations.

cs.GT↗

arXiv2024

Cumulative Hazard Function Based Efficient Multivariate Temporal Point Process Learning

Most existing temporal point process models are characterized by conditional intensity function. These models often require numerical approximation methods for likelihood evaluation, which potentially hurts their performance. By directly modelling the integral of the intensity function, i.e., the cumulative hazard function (CHF), the likelihood can be evaluated accurately, making it a promising approach. However, existing CHF-based methods are not well-defined, i.e., the mathematical constraints of CHF are not completely satisfied, leading to untrustworthy results. For multivariate temporal point process, most existing methods model intensity (or density, etc.) functions for each variate, limiting the scalability. In this paper, we explore using neural networks to model a flexible but well-defined CHF and learning the multivariate temporal point process with low parameter complexity. Experimental results on six datasets show that the proposed model achieves the state-of-the-art performance on data fitting and event prediction tasks while having significantly fewer parameters and memory usage than the strong competitors. The source code and data can be obtained from https://github.com/lbq8942/NPP.

cs.LG↗

arXiv2024

Interpretable Neural Temporal Point Processes for Modelling Electronic Health Records

Electronic Health Records (EHR) can be represented as temporal sequences that record the events (medical visits) from patients. Neural temporal point process (NTPP) has achieved great success in modeling event sequences that occur in continuous time space. However, due to the black-box nature of neural networks, existing NTPP models fall short in explaining the dependencies between different event types. In this paper, inspired by word2vec and Hawkes process, we propose an interpretable framework inf2vec for event sequence modelling, where the event influences are directly parameterized and can be learned end-to-end. In the experiment, we demonstrate the superiority of our model on event prediction as well as type-type influences learning.

cs.LG↗

arXiv2024

Link-aware link prediction over temporal graph by pattern recognition

A temporal graph can be considered as a stream of links, each of which represents an interaction between two nodes at a certain time. On temporal graphs, link prediction is a common task, which aims to answer whether the query link is true or not. To do this task, previous methods usually focus on the learning of representations of the two nodes in the query link. We point out that the learned representation by their models may encode too much information with side effects for link prediction because they have not utilized the information of the query link, i.e., they are link-unaware. Based on this observation, we propose a link-aware model: historical links and the query link are input together into the following model layers to distinguish whether this input implies a reasonable pattern that ends with the query link. During this process, we focus on the modeling of link evolution patterns rather than node representations. Experiments on six datasets show that our model achieves strong performances compared with state-of-the-art baselines, and the results of link prediction are interpretable. The code and datasets are available on the project website: https://github.com/lbq8942/TGACN.

cs.AI↗

arXiv2023

Uncovering Gender Stereotypes in Video Game Character Designs: A Multi-Modal Analysis of Honor of Kings

In this paper, we conduct a comprehensive analysis of gender stereotypes in the character design of Honor of Kings, a popular multiplayer online battle arena (MOBA) game in China. We probe gender stereotypes through the lens of role assignments, visual designs, spoken lines, and background stories, combining qualitative analysis and text mining based on the moral foundation theory. Male heroes are commonly designed as masculine fighters with power and female heroes as feminine "ornaments" with ideal looks. We contribute with a culture-aware and multi-modal understanding of gender stereotypes in games, leveraging text-, visual-, and role-based evidence.

cs.HC↗

arXiv2021

An electric vehicle charging station access equilibrium model with M/D/C queueing

Despite the dependency of electric vehicle (EV) fleets on charging station availability, charging infrastructure remains limited in many cities. Three contributions are made. First, we propose an EV-to-charging station user equilibrium (UE) assignment model with a M/D/C queue approximation as a nondifferentiable nonlinear program. Second, to address the non-differentiability of the queue delay function, we propose an original solution algorithm based on the derivative-free Method of Successive Averages. Computational tests with a toy network show that the model converges to a UE. A working code in Python is provided free on Github with detailed test cases. Third, the model is applied to the large-scale case study of New York City Department of Citywide Administrative Services (NYC DCAS) fleet and EV charging station configuration as of July 8, 2020, which includes unique, real data for 563 Level 2 chargers and 4 Direct Current Fast Chargers (DCFCs) and 1484 EVs distributed over 512 Traffic Analysis Zones. The arrival rates of the assignment model are calibrated in the base scenario to fit an observed average utilization ratio of 7.6% in NYC. The model is then applied to compare charging station investment policies of DCFCs to Level 2 charging stations based on two alternative criteria. Results suggest a policy based on selecting locations with high utilization ratio instead of with high queue delay.

cs.CY↗