arXiv subjects

Haoyang Yu

Publications and source records attributed to Haoyang Yu.

16 recordsLinked to original sources

arXiv2026

Design-based edge-level causal inference with machine learning assisted covariate adjustment

We study design-based causal inference for edge-level outcomes in directed networks under dyadic interference. In this setting, outcomes are defined on directed edges and depend on the joint treatment assignments of pairs of units, inducing a complex dependence structure that invalidates standard estimation and inference procedures developed for node-level data. We construct Horvitz--Thompson estimators for a general class of edge-level causal effects and establish their asymptotic normality under mild regularity conditions. To enable valid inference, we develop variance estimators that exploit identifiable components of network dependence, yielding substantially less conservative bounds than classical approaches. To improve efficiency, we incorporate auxiliary covariates through a sample splitting and cross-fitting procedure. A key technical challenge is that standard two-fold sample splitting fails in the presence of edge-level outcomes due to the dependence induced by shared units. To address this issue, we introduce a three-fold sample splitting and cross-fitting scheme that restores the conditional independence required for unbiased estimation. Under a stability condition, the resulting covariate-adjusted estimator is asymptotically normal and accommodates both linear adjustment and flexible machine learning methods. We further introduce a calibration step that guarantees no asymptotic efficiency loss relative to the unadjusted estimator. Simulation studies and a real-data application confirm the theoretical results and demonstrate substantial efficiency gains.

stat.ME↗

arXiv2025

Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench

The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for accurate physical outcome modeling under diverse conditions. However, existing video benchmarks are physical commonsense-based, offering limited insight into video models' scientific reasoning capability. We introduce VideoScience-Bench, a benchmark designed to evaluate undergraduate-level scientific understanding in video models. Each prompt encodes a composite scientific scenario that requires understanding and reasoning across multiple scientific concepts to generate the correct phenomenon. The benchmark comprises 200 carefully curated prompts spanning 14 topics and 103 concepts in physics and chemistry. We conduct expert-annotated evaluations across seven state-of-the-art video models in T2V and I2V settings along five dimensions: Prompt Consistency, Phenomenon Congruency, Correct Dynamism, Immutability, and Spatio-Temporal Continuity. Using a VLM-as-a-Judge to assess video generations, we observe strong correlation with human assessments. To the best of our knowledge, VideoScience-Bench is the first benchmark to evaluate video models not only as generators but also as reasoners, requiring their generations to demonstrate scientific understanding consistent with expected physical and chemical phenomena. Our data and evaluation code are available at: \href{https://github.com/hao-ai-lab/VideoScience}{github.com/hao-ai-lab/VideoScience}.

cs.CV↗

arXiv2025

Design-based theory for causal inference

Causal inference, as a major research area in statistics and data science, plays a central role across diverse fields such as medicine, economics, education, and the social sciences. Design-based causal inference begins with randomized experiments and emphasizes conducting statistical inference by leveraging the known randomization mechanism, thereby enabling identification and estimation of causal effects under weak model dependence. Grounded in the seminal works of Fisher and Neyman, this paradigm has evolved to include various design strategies, such as stratified randomization and rerandomization, and analytical methods including Fisher randomization tests, Neyman-style asymptotic inference, and regression adjustment. In recent years, with the emergence of complex settings involving high-dimensional data, individual noncompliance, and network interference, design-based causal inference has witnessed remarkable theoretical and methodological advances. This paper provides a systematic review of recent progress in this field, focusing on covariate-balanced randomization designs, design-based statistical inference methods, and their extensions to high-dimensional, noncompliance, and network interference scenarios. It concludes with a comprehensive perspective on future directions for the theoretical development and practical applications of causal inference.

stat.ME↗

arXiv2025

General Modular Harness for LLM Agents in Multi-Turn Gaming Environments

We introduce a modular harness design for LLM agents that composes of perception, memory, and reasoning components, enabling a single LLM or VLM backbone to tackle a wide spectrum of multi turn gaming environments without domain-specific engineering. Using classic and modern game suites as low-barrier, high-diversity testbeds, our framework provides a unified workflow for analyzing how each module affects performance across dynamic interactive settings. Extensive experiments demonstrate that the harness lifts gameplay performance consistently over un-harnessed baselines and reveals distinct contribution patterns, for example, memory dominates in long-horizon puzzles while perception is critical in vision noisy arcades. These findings highlight the effectiveness of our modular harness design in advancing general-purpose agent, given the familiarity and ubiquity of games in everyday human experience.

cs.AI↗

arXiv2025

lmgame-Bench: How Good are LLMs at Playing Games?

Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges in using popular video games to evaluate modern LLMs and find that directly dropping LLMs into games cannot make an effective evaluation, for three reasons -- brittle vision perception, prompt sensitivity, and potential data contamination. We introduce lmgame-Bench to turn games into reliable evaluations. lmgame-Bench features a suite of platformer, puzzle, and narrative games delivered through a unified Gym-style API and paired with lightweight perception and memory scaffolds, and is designed to stabilize prompt variance and remove contamination. Across 13 leading models, we show lmgame-Bench is challenging while still separating models well. Correlation analysis shows that every game probes a unique blend of capabilities often tested in isolation elsewhere. More interestingly, performing reinforcement learning on a single game from lmgame-Bench transfers both to unseen games and to external planning tasks. Our evaluation code is available at https://github.com/lmgame-org/GamingAgent/lmgame-bench.

cs.AI↗

arXiv2025

Light-YOLOv8-Flame: A Lightweight High-Performance Flame Detection Algorithm

Fire detection algorithms, particularly those based on computer vision, encounter significant challenges such as high computational costs and delayed response times, which hinder their application in real-time systems. To address these limitations, this paper introduces Light-YOLOv8-Flame, a lightweight flame detection algorithm specifically designed for fast and efficient real-time deployment. The proposed model enhances the YOLOv8 architecture through the substitution of the original C2f module with the FasterNet Block module. This new block combines Partial Convolution (PConv) and Convolution (Conv) layers, reducing both computational complexity and model size. A dataset comprising 7,431 images, representing both flame and non-flame scenarios, was collected and augmented for training purposes. Experimental findings indicate that the modified YOLOv8 model achieves a 0.78% gain in mean average precision (mAP) and a 2.05% boost in recall, while reducing the parameter count by 25.34%, with only a marginal decrease in precision by 0.82%. These findings highlight that Light-YOLOv8-Flame offers enhanced detection performance and speed, making it well-suited for real-time fire detection on resource-constrained devices.

cs.CV↗

arXiv2025

Minimax Optimal Design with Spillover and Carryover Effects

In various applications, the potential outcome of a unit may be influenced by the treatments received by other units, a phenomenon known as interference, as well as by prior treatments, referred to as carryover effects. These phenomena violate the stable unit treatment value assumption and pose significant challenges in causal inference. To address these complexities, we propose a minimax optimal experimental design that simultaneously accounts for both spillover and carryover effects, enhancing the precision of estimates for direct and spillover effects. This method is particularly applicable to multi-unit experiments, reducing sample size requirements and experimental costs. We also investigate the asymptotic properties of the Horvitz--Thompson estimators of direct and spillover effects, demonstrating their consistency and asymptotic normality under the minimax optimal design. To facilitate valid inferences, we propose conservative variance estimators. Furthermore, we tackle the challenges associated with potential misspecifications in the order of carryover effects. Our approach is validated by comprehensive numerical studies that demonstrate superior performance compared to existing experimental designs.

stat.ME↗

arXiv2024

Combining Priors with Experience: Confidence Calibration Based on Binomial Process Modeling

Confidence calibration of classification models is a technique to estimate the true posterior probability of the predicted class, which is critical for ensuring reliable decision-making in practical applications. Existing confidence calibration methods mostly use statistical techniques to estimate the calibration curve from data or fit a user-defined calibration function, but often overlook fully mining and utilizing the prior distribution behind the calibration curve. However, a well-informed prior distribution can provide valuable insights beyond the empirical data under the limited data or low-density regions of confidence scores. To fill this gap, this paper proposes a new method that integrates the prior distribution behind the calibration curve with empirical data to estimate a continuous calibration curve, which is realized by modeling the sampling process of calibration data as a binomial process and maximizing the likelihood function of the binomial process. We prove that the calibration curve estimating method is Lipschitz continuous with respect to data distribution and requires a sample size of $3/B$ of that required for histogram binning, where $B$ represents the number of bins. Also, a new calibration metric ($TCE_{bpm}$), which leverages the estimated calibration curve to estimate the true calibration error (TCE), is designed. $TCE_{bpm}$ is proven to be a consistent calibration measure. Furthermore, realistic calibration datasets can be generated by the binomial process modeling from a preset true calibration curve and confidence score distribution, which can serve as a benchmark to measure and compare the discrepancy between existing calibration metrics and the true calibration error. The effectiveness of our calibration method and metric are verified in real-world and simulated data.

stat.ME↗

arXiv2024

Sharp variance estimator and causal bootstrap in stratified randomized experiments

Randomized experiments are the gold standard for estimating treatment effects, and randomization serves as a reasoned basis for inference. In widely used stratified randomized experiments, randomization-based finite-population asymptotic theory enables valid inference for the average treatment effect, relying on normal approximation and a Neyman-type conservative variance estimator. However, when the sample size is small or the outcomes are skewed, the Neyman-type variance estimator may become overly conservative, and the normal approximation can fail. To address these issues, we propose a sharp variance estimator and two causal bootstrap methods to more accurately approximate the sampling distribution of the weighted difference-in-means estimator in stratified randomized experiments. The first causal bootstrap procedure is based on rank-preserving imputation and we prove its second-order refinement over normal approximation. The second causal bootstrap procedure is based on constant-treatment-effect imputation and is further applicable in paired experiments. In contrast to traditional bootstrap methods, where randomness originates from hypothetical super-population sampling, our analysis for the proposed causal bootstrap is randomization-based, relying solely on the randomness of treatment assignment in randomized experiments. Numerical studies and two real data applications demonstrate advantages of our proposed methods in finite samples. The \texttt{R} package \texttt{CausalBootstrap} implementing our method is publicly available.

math.ST↗

arXiv2023

Potato: A Data-Oriented Programming 3D Simulator for Large-Scale Heterogeneous Swarm Robotics

Large-scale simulation with realistic nonlinear dynamic models is crucial for algorithms development for swarm robotics. However, existing platforms are mainly developed based on Object-Oriented Programming (OOP) and either use simple kinematic models to pursue a large number of simulating nodes or implement realistic dynamic models with limited simulating nodes. In this paper, we develop a simulator based on Data-Oriented Programming (DOP) that utilizes GPU parallel computing to achieve large-scale swarm robotic simulations. Specifically, we use a multi-process approach to simulate heterogeneous agents and leverage PyTorch with GPU to simulate homogeneous agents with a large number. We test our approach using a nonlinear quadrotor model and demonstrate that this DOP approach can maintain almost the same computational speed when quadrotors are less than 5,000. We also provide two examples to present the functionality of the platform.

cs.RO↗

arXiv2023

Bitcoin Gold, Litecoin Silver:An Introduction to Cryptocurrency's Valuation and Trading Strategy

Historically, gold and silver have played distinct roles in traditional monetary systems. While gold has primarily been revered as a superior store of value, prompting individuals to hoard it, silver has commonly been used as a medium of exchange. As the financial world evolves, the emergence of cryptocurrencies has introduced a new paradigm of value and exchange. However, the store-of-value characteristic of these digital assets remains largely uncharted. Charlie Lee, the founder of Litecoin, once likened Bitcoin to gold and Litecoin to silver. To validate this analogy, our study employs several metrics, including unspent transaction outputs (UTXO), spent transaction outputs (STXO), Weighted Average Lifespan (WAL), CoinDaysDestroyed (CDD), and public on-chain transaction data. Furthermore, we've devised trading strategies centered around the Price-to-Utility (PU) ratio, offering a fresh perspective on crypto-asset valuation beyond traditional utilities. Our back-testing results not only display trading indicators for both Bitcoin and Litecoin but also substantiate Lee's metaphor, underscoring Bitcoin's superior store-of-value proposition relative to Litecoin. We anticipate that our findings will drive further exploration into the valuation of crypto assets. For enhanced transparency and to promote future research, we've made our datasets available on Harvard Dataverse and shared our Python code on GitHub as open source.

cs.CE↗

arXiv2023

Nonlinear MPC for Quadrotors in Close-Proximity Flight with Neural Network Downwash Prediction

Swarm aerial robots are required to maintain close proximity to successfully traverse narrow areas in cluttered environments. However, this movement is affected by the downwash effect generated from other quadrotors in the swarm. This aerodynamic effect is highly nonlinear and hard to describe through mathematical modeling. Additionally, the existence of the downwash disturbance can be predicted based on the states of neighboring quadrotors. If this prediction is considered, the control loop can proactively handle the disturbance, resulting in improved performance. To address these challenges, we propose an approach that integrates a Neural network Downwash Predictor with Nonlinear Model Predictive Control (NDP-NMPC). The neural network is trained with spectral normalization to ensure robustness and safety in uncollected cases. The predicted disturbances are then incorporated into the optimization scheme in NMPC, which enforces constraints to ensure that states and inputs remain within safe limits. We also design a quadrotor system, identify its parameters, and implement the proposed method on board. Finally, we conduct a prediction experiment to validate the safety and effectiveness of the network. In addition, a real-time trajectory tracking experiment is performed with the entire system, demonstrating a 75.37% reduction in tracking error in height under the downwash effect.

cs.RO↗

arXiv2021

Multitask Learning for Citation Purpose Classification

We present our entry into the 2021 3C Shared Task Citation Context Classification based on Purpose competition. The goal of the competition is to classify a citation in a scientific article based on its purpose. This task is important because it could potentially lead to more comprehensive ways of summarizing the purpose and uses of scientific articles, but it is also difficult, mainly due to the limited amount of available training data in which the purposes of each citation have been hand-labeled, along with the subjectivity of these labels. Our entry in the competition is a multi-task model that combines multiple modules designed to handle the problem from different perspectives, including hand-generated linguistic features, TF-IDF features, and an LSTM-with-attention model. We also provide an ablation study and feature analysis whose insights could lead to future work.

cs.LG↗

arXiv2021

Using Low-rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing

Tensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-order tensor, which can perfectly retain the spatial information in the image. In this article, we extend the linear tensor method to the nonlinear tensor method and propose a nonlinear low-rank tensor unmixing algorithm to solve the generalized bilinear model (GBM). Specifically, the linear and nonlinear parts of the GBM can both be expressed as tensors. Furthermore, the low-rank structures of abundance maps and nonlinear interaction abundance maps are exploited by minimizing their nuclear norm, thus taking full advantage of the high spatial correlation in HSIs. Synthetic and real-data experiments show that the low rank of abundance maps and nonlinear interaction abundance maps exploited in our method can improve the performance of the nonlinear unmixing. A MATLAB demo of this work will be available at https://github.com/LinaZhuang for the sake of reproducibility.

cs.CV↗

arXiv2021

Construction of Nahm data and BPS monopoles with continuous symmetries

We study solutions to Nahm's equations with continuous symmetries and, under certain (mild) hypotheses, we classify the corresponding Ans\"atze. Using our classification, we construct novel Nahm data, and prescribe methods for generating further solutions. Finally, we use these results to construct new BPS monopoles with spherical symmetry.

math-ph↗

arXiv2020

Confused Modulo Projection based Somewhat Homomorphic Encryption -- Cryptosystem, Library and Applications on Secure Smart Cities

With the development of cloud computing, the storage and processing of massive visual media data has gradually transferred to the cloud server. For example, if the intelligent video monitoring system cannot process a large amount of data locally, the data will be uploaded to the cloud. Therefore, how to process data in the cloud without exposing the original data has become an important research topic. We propose a single-server version of somewhat homomorphic encryption cryptosystem based on confused modulo projection theorem named CMP-SWHE, which allows the server to complete blind data processing without \emph{seeing} the effective information of user data. On the client side, the original data is encrypted by amplification, randomization, and setting confusing redundancy. Operating on the encrypted data on the server side is equivalent to operating on the original data. As an extension, we designed and implemented a blind computing scheme of accelerated version based on batch processing technology to improve efficiency. To make this algorithm easy to use, we also designed and implemented an efficient general blind computing library based on CMP-SWHE. We have applied this library to foreground extraction, optical flow tracking and object detection with satisfactory results, which are helpful for building smart cities. We also discuss how to extend the algorithm to deep learning applications. Compared with other homomorphic encryption cryptosystems and libraries, the results show that our method has obvious advantages in computing efficiency. Although our algorithm has some tiny errors ($10^{-6}$) when the data is too large, it is very efficient and practical, especially suitable for blind image and video processing.

cs.CR↗