arXiv subjects

Yunyi Li

Publications and source records attributed to Yunyi Li.

17 recordsLinked to original sources

arXiv2026

DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking

Video generation models achieve high visual quality but often struggle to generate physics-aware videos. Unlike rigid-body motion, which can be described by explicit trajectories or formulas, complex deformation dynamics remain challenging to synthesize. We observe that a lack of physical reasoning for localizing dynamic areas allows irrelevant regions to dilute the model's attention, leading to generation failure. In this paper, we propose DeforM, a reasoning-guided image-to-video generation framework that directs the model's focus toward physics-critical regions. To reason about and localize these critical regions, we introduce a VLM-guided physical reasoning module, DeforM-Reason, to identify target objects and generate spatial-temporal masks. For physical guidance, we develop two alternative strategies: DeforM-Free for training-free mechanism analysis and DeforM-Injection as a powerful training-based generator. Experimental results demonstrate that DeforM improves the realism of generated deformation scenarios, outperforming baseline models in both visual quality and physical consistency.

cs.CV↗

arXiv2026

Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking

Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, $P(y=1 \mid o_{1:t})$, using prefix-safe observations. Sequential Bayesian Belief Tracking (SBBT) calibrates observation likelihoods and recursively updates a two-state belief, providing a common tracker for scalar scores, text and self-verification markers, hidden clusters, token-pooling probes, and latent-trajectory features. Across generated open-weight traces on MATH-500, GSM8K, AIME 2025, and RIMO-N, probability quality and ranking separate: score-only SBBT often improves Brier, while AUROC gains require structure-aware evidence beyond strong prefix-safe baselines. In the strongest hard math setting, structure-aware observations reach +0.110 AUROC against standard prefix-safe baselines. Under a same-prefix classifier audit, MATH-500 text markers and RIMO-N self-verification signals remain positive. Together, these findings support SBBT as a calibration-aware online inference framework and expose an evidence regime: scalar scores mainly support probability quality, while structure-aware prefix signals support ranking only when strong prefix-safe baselines have not already absorbed the rank evidence.

cs.AI↗

arXiv2026

Your Simulation Runs but Solves the Wrong Physics: PDE-Grounded Intent Verification for LLM-Generated Multiphysics Simulation Code

Execution-based evaluation of LLM-generated code implicitly treats successful execution as a proxy for correctness. In scientific simulation, this proxy is insufficient: a generated input file can run, mesh, and converge while encoding governing equations that differ from the user's intent. We call this mismatch between intended physics and generated code the comprehension-generation gap. We instantiate this in MOOSE, where Kernel and BC objects map compositionally to weak-form residual terms, enabling deterministic reconstruction of the encoded PDE and comparison against an intended contract. We formalize this comparison as the Intent Fidelity Score (IFS), a structural metric covering governing terms, BCs, ICs, coefficients, and time scheme. Building on IFS, we develop a PDE-grounded refinement loop that uses deterministic violation reports to correct generated code iteratively. We evaluate on MooseBench, a 220-case multiphysics benchmark with PDE-level ground truth released with this work. On this benchmark, our method consistently improves mean IFS over direct generation, with gains concentrated on hard cases. On the subset where direct generation falls below IFS 0.7, refinement adds +0.22 to +0.41 absolute IFS. In the deployment audit, execution-only repair improves execution success while leaving 39-40% of all 220 cases runnable but still solving the wrong physics across the three main deployment-audit models, exposing executability and intent fidelity as separable failure modes. Static proof-of-concept experiments on four PDE-oriented DSLs (UFL/FEniCS, FreeFEM, FiPy, and Devito) suggest that the reconstruction-and-comparison pattern extends beyond MOOSE. These findings reinforce that executable simulation code should be verified against the mathematical structure it is intended to encode, not accepted on execution alone.

cs.LG↗

arXiv2026

Synchronization-Safe Dynamic Microgrid Formation for DER-Led Distribution System Restoration With Constraint-Aware Graph Learning

Prolonged blackouts in distribution systems (DSs) with high penetration of distributed energy resources (DERs) necessitate novel restoration strategies to rapidly restore loads. However, the resulting complex optimization problem significantly limits scalability. This paper proposes a synchronization-safe dynamic microgrid (MG) formation (SSDMGF)-enabled restoration framework, in which a constraint-aware graph learning approach is developed to enhance solution efficiency. To characterize the restoration status of systems with evolving boundaries, the concepts of system mode and system class are defined. To ensure synchronization safety during restoration, the transitions of system mode and class for dynamically formed MGs are explicitly restricted. To further accelerate the solution process, a constraint-aware spatio-temporal graph convolutional network (STGCN) is designed to partially generate high-quality warm-start solutions, where synchronization-related constraints are embedded into a differentiable feasibility-resolving layer based on the straight-through estimator (STE). Case studies on a modified IEEE 123-node feeder validate that the proposed method ensures synchronization-safe MG formation and improves restoration performance. Meanwhile, the proposed acceleration framework achieves significant computational speed-ups without compromising final optimality.

eess.SY↗

arXiv2025

Exploiting Convexity of Neural Networks in Dynamic Operating Envelope Optimization for Distributed Energy Resources

The increasing penetration of distributed energy resources (DERs) brings opportunities and challenges to the operation of distribution systems. To ensure network integrity, dynamic operating envelopes (DOEs) are issued by utilities to DERs as their time-varying export/import power limits. Due to the non-convex nature of power flow equations, the optimization of DOEs faces a dilemma of solution accuracy and computation efficiency. To bridge this gap, in this paper, we facilitate DOE optimization by exploiting the convexity of input convex neural networks (ICNNs). A DOE optimization model is first presented, comprehensively considering multiple operational constraints. We propose a constraint embedding method that allows us to replace the non-convex power flow constraints with trained ICNN models and convexify the problem. To further speed up DOE optimization, we propose a linear relaxation of the ICNN-based DOE optimization problem, for which the tightness is theoretically proven. The effectiveness of the proposed method is validated with numerical case studies. Results show that the proposed ICNN-based method outperforms other benchmark methods in optimizing DOEs in terms of both solution quality and solution time.

eess.SY↗

arXiv2025

Bias-Aware Mislabeling Detection via Decoupled Confident Learning

Reliable data is a cornerstone of modern organizational systems. A notable data integrity challenge stems from label bias, which refers to systematic errors in a label, a covariate that is central to a quantitative analysis, such that its quality differs across social groups. This type of bias has been conceptually and empirically explored and is widely recognized as a pressing issue across critical domains. However, effective methodologies for addressing it remain scarce. In this work, we propose Decoupled Confident Learning (DeCoLe), a principled machine learning based framework specifically designed to detect mislabeled instances in datasets affected by label bias, enabling bias aware mislabelling detection and facilitating data quality improvement. We theoretically justify the effectiveness of DeCoLe and evaluate its performance in the impactful context of hate speech detection, a domain where label bias is a well documented challenge. Empirical results demonstrate that DeCoLe excels at bias aware mislabeling detection, consistently outperforming alternative approaches for label error detection. Our work identifies and addresses the challenge of bias aware mislabeling detection and offers guidance on how DeCoLe can be integrated into organizational data management practices as a powerful tool to enhance data reliability.

cs.LG↗

arXiv2025

A Point-Hyperplane Geometry Method for Operational Security Region of Renewable Energy Generation in Power Systems

The rapid growth of renewable energy generation challenges the secure operation of power systems. It becomes crucial to quantify the critical security boundaries and hosting capability of renewable generation at the system operation level. This paper proposes a novel point-hyperplane geometry (PHG) method to accurately obtain the geometric expression of the operational security region of renewable energy generation for power systems. Firstly, the geometric expression of the operational security region is defined as a polytope of boundary hyperplanes in the form of inequalities satisfying the system operation constraints. Then, an orthogonal basis generation method is proposed to solve a single boundary hyperplane of the polytope based on intersecting and orthogonal geometric principles. Next, a point-hyperplane iteration algorithm is developed to progressively obtain the overall geometric polytope of the operational security region of renewable energy generation in power systems. Besides, the flexible performance trade-off can be achieved by modifying the proposed maximum tolerated angle between adjacent hyperplanes. Finally, comprehensive case studies verify the effectiveness and superiority of the PHG method.

eess.SY↗

arXiv2023

Mitigating Label Bias via Decoupled Confident Learning

Growing concerns regarding algorithmic fairness have led to a surge in methodologies to mitigate algorithmic bias. However, such methodologies largely assume that observed labels in training data are correct. This is problematic because bias in labels is pervasive across important domains, including healthcare, hiring, and content moderation. In particular, human-generated labels are prone to encoding societal biases. While the presence of labeling bias has been discussed conceptually, there is a lack of methodologies to address this problem. We propose a pruning method -- Decoupled Confident Learning (DeCoLe) -- specifically designed to mitigate label bias. After illustrating its performance on a synthetic dataset, we apply DeCoLe in the context of hate speech detection, where label bias has been recognized as an important challenge, and show that it successfully identifies biased labels and outperforms competing approaches.

cs.LG↗

arXiv2022

More Data Can Lead Us Astray: Active Data Acquisition in the Presence of Label Bias

An increased awareness concerning risks of algorithmic bias has driven a surge of efforts around bias mitigation strategies. A vast majority of the proposed approaches fall under one of two categories: (1) imposing algorithmic fairness constraints on predictive models, and (2) collecting additional training samples. Most recently and at the intersection of these two categories, methods that propose active learning under fairness constraints have been developed. However, proposed bias mitigation strategies typically overlook the bias presented in the observed labels. In this work, we study fairness considerations of active data collection strategies in the presence of label bias. We first present an overview of different types of label bias in the context of supervised learning systems. We then empirically show that, when overlooking label bias, collecting more data can aggravate bias, and imposing fairness constraints that rely on the observed labels in the data collection process may not address the problem. Our results illustrate the unintended consequences of deploying a model that attempts to mitigate a single type of bias while neglecting others, emphasizing the importance of explicitly differentiating between the types of bias that fairness-aware algorithms aim to address, and highlighting the risks of neglecting label bias during data collection.

cs.LG↗

arXiv2022

Nonconvex ${L_ {1/2}} $-Regularized Nonlocal Self-similarity Denoiser for Compressive Sensing based CT Reconstruction

Compressive sensing (CS) based computed tomography (CT) image reconstruction aims at reducing the radiation risk through sparse-view projection data. It is usually challenging to achieve satisfying image quality from incomplete projections. Recently, the nonconvex ${L_ {1/2}} $-norm has achieved promising performance in sparse recovery, while the applications on imaging are unsatisfactory due to its nonconvexity. In this paper, we develop a ${L_ {1/2}} $-regularized nonlocal self-similarity (NSS) denoiser for CT reconstruction problem, which integrates low-rank approximation with group sparse coding (GSC) framework. Concretely, we first split the CT reconstruction problem into two subproblems, and then improve the CT image quality furtherly using our ${L_ {1/2}} $-regularized NSS denoiser. Instead of optimizing the nonconvex problem under the perspective of GSC, we particularly reconstruct CT image via low-rank minimization based on two simple yet essential schemes, which build the equivalent relationship between GSC based denoiser and low-rank minimization. Furtherly, the weighted singular value thresholding (WSVT) operator is utilized to optimize the resulting nonconvex ${L_ {1/2}} $ minimization problem. Following this, our proposed denoiser is integrated with the CT reconstruction problem by alternating direction method of multipliers (ADMM) framework. Extensive experimental results on typical clinical CT images have demonstrated that our approach can further achieve better performance than popular approaches.

eess.IV↗

arXiv2021

Edge-Enhanced Global Disentangled Graph Neural Network for Sequential Recommendation

Sequential recommendation has been a widely popular topic of recommender systems. Existing works have contributed to enhancing the prediction ability of sequential recommendation systems based on various methods, such as recurrent networks and self-attention mechanisms. However, they fail to discover and distinguish various relationships between items, which could be underlying factors which motivate user behaviors. In this paper, we propose an Edge-Enhanced Global Disentangled Graph Neural Network (EGD-GNN) model to capture the relation information between items for global item representation and local user intention learning. At the global level, we build a global-link graph over all sequences to model item relationships. Then a channel-aware disentangled learning layer is designed to decompose edge information into different channels, which can be aggregated to represent the target item from its neighbors. At the local level, we apply a variational auto-encoder framework to learn user intention over the current sequence. We evaluate our proposed method on three real-world datasets. Experimental results show that our model can get a crucial improvement over state-of-the-art baselines and is able to distinguish item features.

cs.IR↗

arXiv2021

Gaussian Process Regression and Classification using International Classification of Disease Codes as Covariates

International Classification of Disease (ICD) codes are widely used for encoding diagnoses in electronic health records (EHR). Automated methods have been developed over the years for predicting biomedical responses using EHR that borrow information among diagnostically similar patients. Relatively less attention has been paid to developing patient similarity measures that model the structure of ICD codes and the presence of multiple chronic conditions, where a chronic condition is defined as a set of ICD codes. Motivated by this problem, we first develop a type of string kernel function for measuring similarity between a pair of subsets of ICD codes, which uses the definition of chronic conditions. Second, we extend this similarity measure to define a family of covariance functions on subsets of ICD codes. Using this family, we develop Gaussian process (GP) priors for Bayesian nonparametric regression and classification using diagnoses and other demographic information as covariates. Markov chain Monte Carlo (MCMC) algorithms are used for posterior inference and predictions. The proposed methods are free of any tuning parameters and are well-suited for automated prediction of continuous and categorical biomedical responses that depend on chronic conditions. We evaluate the practical performance of our method on EHR data collected from 1660 patients at the University of Iowa Hospitals and Clinics (UIHC) with six different primary cancer sites. Our method has better sensitivity and specificity than its competitors in classifying different primary cancer sites and estimates the marginal associations between chronic conditions and primary cancer sites.

stat.ME↗

arXiv2021

Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning

We propose Partially Interpretable Estimators (PIE) which attribute a prediction to individual features via an interpretable model, while a (possibly) small part of the PIE prediction is attributed to the interaction of features via a black-box model, with the goal to boost the predictive performance while maintaining interpretability. As such, the interpretable model captures the main contributions of features, and the black-box model attempts to complement the interpretable piece by capturing the "nuances" of feature interactions as a refinement. We design an iterative training algorithm to jointly train the two types of models. Experimental results show that PIE is highly competitive to black-box models while outperforming interpretable baselines. In addition, the understandability of PIE is comparable to simple linear models as validated via a human evaluation.

cs.LG↗

arXiv2020

ADMM-IDNN: Iteratively Double-reweighted Nuclear Norm Algorithm for Group-prior based Nonconvex Compressed Sensing via ADMM

Group-prior based regularization method has led to great successes in various image processing tasks, which can usually be considered as a low-rank matrix minimization problem. As a widely used surrogate function of low-rank, the nuclear norm based convex surrogate usually lead to over-shrinking phenomena, since the nuclear norm shrinks the rank components (singular value) simultaneously. In this paper, we propose a novel Group-prior based nonconvex image compressive sensing (CS) reconstruction framework via a family of nonconvex nuclear norms functions which contain common concave and monotonically properties. To solve the resulting nonconvex nuclear norm minimization (NNM) problem, we develop a Group based iteratively double-reweighted nuclear norm algorithm (IDNN) via an alternating direction method of multipliers (ADMM) framework. Our proposed algorithm can convert the nonconvex nuclear norms optimization problem into a double-reweighted singular value thresholding (DSVT) problem. Extensive experiments demonstrate our proposed framework achieved favorable reconstruction performance compared with current state-of-the-art convex methods.

eess.IV↗

arXiv2020

From Group Sparse Coding to Rank Minimization: A Novel Denoising Model for Low-level Image Restoration

Recently, low-rank matrix recovery theory has been emerging as a significant progress for various image processing problems. Meanwhile, the group sparse coding (GSC) theory has led to great successes in image restoration (IR) problem with each group contains low-rank property. In this paper, we propose a novel low-rank minimization based denoising model for IR tasks under the perspective of GSC, an important connection between our denoising model and rank minimization problem has been put forward. To overcome the bias problem caused by convex nuclear norm minimization (NNM) for rank approximation, a more generalized and flexible rank relaxation function is employed, namely weighted nonconvex relaxation. Accordingly, an efficient iteratively-reweighted algorithm is proposed to handle the resulting minimization problem combing with the popular L_(1/2) and L_(2/3) thresholding operators. Finally, our proposed denoising model is applied to IR problems via an alternating direction method of multipliers (ADMM) strategy. Typical IR experiments on image compressive sensing (CS), inpainting, deblurring and impulsive noise removal demonstrate that our proposed method can achieve significantly higher PSNR/FSIM values than many relevant state-of-the-art methods.

eess.IV↗

arXiv2020

Nonconvex Nonsmooth Low-Rank Minimization for Generalized Image Compressed Sensing via Group Sparse Representation

Group sparse representation (GSR) based method has led to great successes in various image recovery tasks, which can be converted into a low-rank matrix minimization problem. As a widely used surrogate function of low-rank, the nuclear norm based convex surrogate usually leads to over-shrinking problem, since the standard soft-thresholding operator shrinks all singular values equally. To improve traditional sparse representation based image compressive sensing (CS) performance, we propose a generalized CS framework based on GSR model, which leads to a nonconvex nonsmooth low-rank minimization problem. The popular L_2-norm and M-estimator are employed for standard image CS and robust CS problem to fit the data respectively. For the better approximation of the rank of group-matrix, a family of nuclear norms are employed to address the over-shrinking problem. Moreover, we also propose a flexible and effective iteratively-weighting strategy to control the weighting and contribution of each singular value. Then we develop an iteratively reweighted nuclear norm algorithm for our generalized framework via an alternating direction method of multipliers framework, namely, GSR-AIR. Experimental results demonstrate that our proposed CS framework can achieve favorable reconstruction performance compared with current state-of-the-art methods and the robust CS framework can suppress the outliers effectively.

eess.IV↗

arXiv2018

Next Hit Predictor - Self-exciting Risk Modeling for Predicting Next Locations of Serial Crimes

Our goal is to predict the location of the next crime in a crime series, based on the identified previous offenses in the series. We build a predictive model called Next Hit Predictor (NHP) that finds the most likely location of the next serial crime via a carefully designed risk model. The risk model follows the paradigm of a self-exciting point process which consists of a background crime risk and triggered risks stimulated by previous offenses in the series. Thus, NHP creates a risk map for a crime series at hand. To train the risk model, we formulate a convex learning objective that considers pairwise rankings of locations and use stochastic gradient descent to learn the optimal parameters. Next Hit Predictor incorporates both spatial-temporal features and geographical characteristics of prior crime locations in the series. Next Hit Predictor has demonstrated promising results on decades' worth of serial crime data collected by the Crime Analysis Unit of the Cambridge Police Department in Massachusetts, USA.

stat.AP↗