Searcharxiv⌕ Search

arXiv subjects

Wei Yao

Publications and source records attributed to Wei Yao.

At least 19 recordsLinked to original sources
arXiv2026

Spectral Consistency-Guided Multiview Point Cloud Registration for Low-Overlap Scenes

Multiview point cloud registration is particularly challenging in low-overlap scenes, where reliable correspondences are limited and incorrect pairwise transformations can affect global pose estimation. In addition, registering all scan pairs is computationally expensive because many pairs provide weak geometric information. To address these problems, we propose GMPCR, a non-learning-based spectral consistency-guided framework for efficient and robust multiview point cloud registration. GMPCR builds a refined second-order compatibility structure from initial correspondences and uses its dominant spectral response to evaluate both correspondence reliability and scan-pair confidence. This allows unreliable correspondences to be filtered and informative scan pairs to be selected before relative transformation estimation, leading to a sparse pose graph and reduced pairwise registration cost. For each retained scan pair, maximal-clique-based hypothesis generation is used to estimate reliable relative transformations. The resulting pose graph is further refined by an adaptive history-aware synchronization scheme, in which the effect of residual history is adjusted according to changes in the global rotation residual. A recovery mechanism also allows down-weighted edges to regain confidence when their global consistency improves. Experiments on 3DMatch, 3DLoMatch, ScanNet, and ETH demonstrate the effectiveness of GMPCR. It achieves registration recalls of 97.2% and 89.6% on 3DMatch and 3DLoMatch, respectively, while maintaining competitive performance on ScanNet and ETH. The results show that GMPCR provides a favorable balance among registration accuracy, robustness to low overlap, and computational efficiency. The code is publicly available at https://github.com/swccj/gmpcr.

cs.CV↗
arXiv2026

Semi-Supervised Hyperspectral Image Classification with Edge-Aware Superpixel Label Propagation and Adaptive Pseudo-Labeling

Significant progress has been made in semi-supervised hyperspectral image (HSI) classification regarding feature extraction and classification performance. However, due to high annotation costs and limited sample availability, semi-supervised learning still faces challenges such as boundary label diffusion and pseudo-label instability. To address these issues, this paper proposes a novel semi-supervised hyperspectral classification framework integrating spatial prior information with a dynamic learning mechanism. First, we design an Edge-Aware Superpixel Label Propagation (EASLP) module. By integrating edge intensity penalty with neighborhood correction strategy, it mitigates label diffusion from superpixel segmentation while enhancing classification robustness in boundary regions. Second, we introduce a Dynamic History-Fused Prediction (DHP) method. By maintaining historical predictions and dynamically weighting them with current results, DHP smoothens pseudo-label fluctuations and improves temporal consistency and noise resistance. Concurrently, incorporating condifence and consistency measures, the Adaptive Tripartite Sample Categorization (ATSC) strategy implements hierarchical utilization of easy, ambiguous, and hard samples, leading to enhanced pseudo-label quality and learning efficiency. The Dynamic Reliability-Enhanced Pseudo-Label Framework (DREPL), composed of DHP and ATSC, strengthens pseudo-label stability across temporal and sample domains. Through synergizes operation with EASLP, it achieves spatio-temporal consistency optimization. Evaluations on four benchmark datasets demonstrate its capability to maintain superior classification performance.

cs.CV↗
arXiv2026

Preference-Oriented Aggregation of Heterogeneous Distributed Energy Resources for Reserve Dispatch

Aggregating distributed energy resources (DERs) aims to encode their collective flexibility into a single set for efficient grid dispatch. However, existing aggregation methods are overly conservative for heterogeneous DERs due to two main challenges: 1) dimensional heterogeneity, which complicates the combination of flexibilities across different time dimensions, and 2) type heterogeneity, where diverse and irregular DER profiles hinder accurate approximations, resulting in significant flexibility loss. To resolve these challenges, this paper propose a novel preference-oriented aggregation method for reserve dispatch. For dimensional heterogeneity, we extend existing techniques by reformulating the Minkowski sum as a polytope projection problem using a matrix transformation technique. By unifying DERs in a higher-dimensional space and projecting them back into the aggregate feasible region, the proposed technique effectively aggregates dimensionally heterogeneous DERs. For type heterogeneity, we further develop a distributed aggregation-dispatch coordination framework that incorporates reserve dispatch preferences into aggregation. This framework effectively captures the critical, active aggregate flexibility prioritized in optimal reserve dispatch, thereby significantly reducing the flexibility loss when aggregating type-heterogeneous DERs. Numerical tests validate the effectiveness of our method in addressing both heterogeneities and highlight its promising potential for power systems with high reserve requirements.

eess.SY↗
arXiv2026

Continuous-Time Aggregation of Massive Flexible HVAC Loads Considering Uncertainty for Reserve Provision in Power System Dispatch

Heating, ventilation, and air conditioning (HVAC) loads, with their rapid response capabilities, can provide considerable intra-hour flexibility on the demand side for reserve provision in order to follow the fast variations of renewables. However, scheduling massive HVACs is challenging due to computation complexity and the uncertainty of outdoor temperature. In this paper, we first introduce a novel continuous-time (CT) aggregation model to reveal the potential intra-hour flexibility of HVACs. For accurate aggregation, a new affine transformation is designed to handle the heterogeneity in high-dimensional feasible region. Further, for reliable aggregation in practical environment, the outdoor temperature uncertainty is constructed by distributionally robust chance constrains and integrated into the aggregation model. Secondly, for the tractable calculation of the proposed CT aggregation model, a cascade of tailored reformulation techniques is proposed, including the Bernstein polynomial spline, polytope projection, and linearization transformation. Thirdly, a customized hierarchical dispatch framework is proposed via incorporating the proposed CT aggregation model into reserve provision in power system dispatch, so as to efficiently schedule massive HVACs to cope with the renewable uncertainty. Case studies verify the effectiveness and scalability of the proposed CT aggregation model in aggregation accuracy, intra-hour flexibility utilization, and uncertainty handling.

eess.SY↗
arXiv2026

Weak-to-Strong Generalization via Bregman Bias-Variance Decomposition

Weak-to-strong generalization (W2SG) is the phenomenon in which a powerful student model, trained on labels produced by a weaker teacher, ultimately outperforms the teacher on the target task. In this work, we theoretically investigate how W2SG can arise via a generalized bias-variance decomposition under Bregman divergence. We show that the expected population risk gap between the student and the teacher is characterized by the expected misfit between the two models. Unlike earlier misfit-based analyses, our theory removes several restrictive assumptions, e.g., it does not require the student hypothesis class to be convex. Our results indicate that W2SG is more likely when the student effectively approximates the teacher's posterior mean. Specializing to squared loss, we provide a sufficient condition (illustrated through a concrete example) under which the student converges to its posterior mean teacher; in particular, increasing the student model size can ensure this convergence. For cross-entropy loss, our analysis further suggests that lowering the entropy of the student's predictive distribution can promote W2SG. We also find that the reverse cross-entropy, unlike the standard forward cross-entropy, is less sensitive to the teacher's predictive uncertainty. Finally, we verify these theoretical insights empirically and demonstrate that incorporating reverse cross-entropy consistently improves student performance.

cs.LG↗
arXiv2026

COSTA: A Cluster-Centric Paradigm for Annotation-Free Open-Set Semantic Segmentation of Aerial Point Clouds with Domain Shifts

Semantic segmentation of aerial point cloud is trapped in a generalization crisis under distinct domain shifts. While test-time adaptation offers a privacy-preserving and computationally efficient way to adapt pre-trained models to unlabeled target-domain data during inference, existing methods, bound to closed-set label assumptions and non-scalable point-wise segmentation pipelines, still struggle with semantic shifts. We ask: can we adapt any given pre-trained aerial point cloud segmentation model to a shifted target domain at the inference phase alone, without additional training, while segmenting target-specific categories beyond the source label space on demand? This paper introduces COSTA, which breaks this limitation by shifting from closed-set point-wise adaptation to cluster-centric open-set semantic propagation. Our core discovery is that, once effectively adapted at test time, the rich feature distribution of aerial point clouds can be distilled into a compact set of well-separated semantic centroids that are transferable across label spaces. COSTA leverages this to reformulate open-set semantic segmentation as a cluster-level propagating process: it first bridges the domain gap through proven test-time adaptation, then groups each batch of target-domain points into a small set of semantic clusters based on the similarity distribution in the adapted feature space, and finally propagates high-confidence pseudo labels obtained from an open-vocabulary vision-language model to all points through cluster-level voting. This cluster-centric paradigm enables test-time adaptation of aerial point clouds under significant domain gaps with mixed semantic shifts. With DALES as the source domain, COSTA enables on-demand segmentation across three aerial point cloud benchmarks with distinct domains and heterogeneous category spaces, achieving up to 70.09% mIoU under this new setting.

cs.CV↗
arXiv2026

SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy

Controllable cooperative humanoid manipulation is a fundamental yet challenging problem for embodied intelligence, due to severe data scarcity, complexities in multi-agent coordination, and limited generalization across objects. In this paper, we present SynAgent, a unified framework that enables scalable and physically plausible cooperative manipulation by leveraging Solo-to-Cooperative Agent Synergy to transfer skills from single-agent human-object interaction to multi-agent human-object-human scenarios. To maintain semantic integrity during motion transfer, we introduce an interaction-preserving retargeting method based on an Interact Mesh constructed via Delaunay tetrahedralization, which faithfully maintains spatial relationships among humans and objects. Building upon this refined data, we propose a single-agent pretraining and adaptation paradigm that distills synergistic collaborative behaviors from abundant single-human data through decentralized training and multi-agent PPO. Finally, we develop a trajectory-conditioned generative policy using a conditional VAE, trained via multi-teacher distillation from motion imitation priors to achieve stable and controllable object-level trajectory execution. Extensive experiments demonstrate that SynAgent significantly outperforms existing baselines in both cooperative imitation and trajectory-conditioned control, while generalizing across diverse object geometries. Codes and data will be available after publication. Project Page: https://yw0208.github.io/synagent/

cs.CV↗
arXiv2026

A Provably Convergent Plug-and-Play Framework for Stochastic Bilevel Optimization

Bilevel optimization has recently attracted significant attention in machine learning due to its wide range of applications and advanced hierarchical optimization capabilities. In this paper, we propose a plug-and-play framework, named PnPBO, for developing and analyzing stochastic bilevel optimization methods. This framework integrates both modern unbiased and biased stochastic estimators into the single-loop bilevel optimization framework introduced in [9], with several improvements. In the implementation of PnPBO, all stochastic estimators for different variables can be independently incorporated, and an additional moving average technique is applied when using an unbiased estimator for the upper-level variable. In the theoretical analysis, we provide a unified convergence and complexity analysis for PnPBO, demonstrating that the adaptation of various stochastic estimators (including PAGE, ZeroSARAH, and mixed strategies) within the PnPBO framework achieves optimal sample complexity, comparable to that of single-level optimization. This resolves the open question of whether the optimal complexity bounds for solving bilevel optimization are identical to those for single-level optimization. Finally, we empirically validate our framework, demonstrating its effectiveness on several benchmark problems and confirming our theoretical findings.

math.OC↗
arXiv2026

Resolving Primitive-Sharing Ambiguity in Long-Tailed TLS-Based Industrial MEP Point Cloud Segmentation via Spatial Context Constraints

In terrestrial laser scanning (TLS)-based mechanical, electrical, and plumbing (MEP) point cloud segmentation, safety-critical components such as reducers and valves are persistently misclassifed, blocking reliable engineering knowledge extraction. This stems from a dual crisis--extreme class imbalance (215:1) compounded by geometric ambiguity, since most tail classes share cylindrical primitives with dominant head classes--that existing frequencybased re-weighting methods cannot resolve. We propose spatial context constraints that exploit neighborhood prediction consistency to disambiguate locally similar structures. Our approach extends Class-Balanced (CB) Loss with two architecture-agnostic mechanisms: Boundary-CB, an entropy-based constraint that emphasizes ambiguous boundaries and encodes an MEP assemblytopology prior, and Density-CB, a density-based constraint that compensates for scan-dependent variations and encodes TLS sensor-physics knowledge. Both operate at the loss level and integrate into existing pipelines without backbone modifcations. On the Industrial3D dataset (612.7M labelled points from water treatment facilities), our method achieves 55.74% mIoU, exceeding the strongest of three representative fully supervised backbone baselines (39.83-52.48% mIoU), with a 21.7% relative improvement on tail-class performance (29.59% vs. 24.32%) while preserving head-class accuracy (88.14%). Components with primitive-sharing ambiguity show strong gains: reducer improves from 0% to 21.12% IoU, and valve improves by 24.3% relative. These results show that spatial context constraints reduce primitive-sharing errors in the target industrial MEP setting and support more reliable identifcation of safety-critical components for Digital Twin and Scan-to-BIM applications. Code: https://github.com/PointCloudYC/LongTail3D.git.

cs.CV↗
arXiv2026

Industrial3D: A Water-Treatment TLS Point Cloud Dataset and Cross-Paradigm Benchmark for MEP Scene Understanding

Automated semantic understanding of dense terrestrial laser scanning (TLS) point clouds is a prerequisite for Scan-to-BIM, digital twin maintenance, and as-built verifcation. Yet for operational industrial mechanical, electrical, and plumbing (MEP) facilities, this challenge remains largely unsolved: water-treatment TLS scans exhibit extreme geometric ambiguity, severe occlusion, and extreme class imbalance that architectural benchmarks such as S3DIS and ScanNet cannot adequately represent. We present Industrial3D, a terrestrial LiDAR dataset with 612.7 million expert-labeled points at 6 mm resolution from 20 room scenes, 13 dataset areas, and 7 operational water treatment facilities. At 6.6x the scale of the closest comparable MEP dataset, Industrial3D provides the largest industrial MEP testbed for within-domain scene understanding. We further establish a cross-paradigm benchmark of nine methods across fully supervised, weakly supervised, unsupervised, and foundation-model settings. The best supervised method reaches 55.74% mIoU, whereas zero-shot Point-SAM reaches 15.79%, a 39.95 percentage-point gap that quantifes unresolved domain transfer for industrial TLS data. Analysis attributes this gap to a dual crisis: 215:1 statistical rarity and cylindrical geometric ambiguity between tail classes and head-class pipes. The dataset, benchmark code, and pre-trained models will be publicly released at https://github.com/pointcloudyc/Industrial3D.

cs.CV↗
arXiv2026

Directional first order approach for a class of bilevel programs

In this paper, we study a class of bilevel optimization program, where the feasible set of the lower level program is independent of the upper level variable. For bilevel programs it is known that the first order reformulation of a bilevel program requires the convexity of the lower level program while reformulations involving the value function result in difficult optimization problems. In this paper we propose a directional first order approach which does not require convexity of the lower level program. First, we propose some conditions under which the lower level program can be equivalently characterized by its first order condition over a directional neighborhood around the local optimal condition. Next we give some conditions under which the classical first order optimality condition in the form of M-stationary condition still holds as a necessary optimality condition for the first order reformulation of the bilevel program even when the lower level program is nonconvex.

math.OC↗
arXiv2026

On the Blessing of Pre-training in Weak-to-Strong Generalization

The paradigm of Weak-to-Strong Generalization (W2SG) suggests that a pre-trained strong model can surpass its weak supervisor, yet the decisive role of pre-training remains theoretically and empirically under-explored. In this work, we identify pre-training as the essential prerequisite for the emergence of W2SG. Theoretically, we formalize the W2SG problem within a high-dimensional single-index model framework using spiked Gaussian data, modeling pre-training as a spectral initialization step. Building upon prior impossibility results regarding the failure of learning under random initialization, we prove that W2SG is achievable when pre-training provides a geometric warm start that places the model within an "effective region" characterized by a perturbed strong-convexity geometry. Within this region, we derive a rigorous generalization bound that naturally captures the optimization dynamics: an initial performance improvement followed by a saturation bottleneck dictated by the weak supervisor's bias. Empirically, we first validate all our assumptions and theoretical insights through controlled synthetic simulations. Finally, through a massive-scale evaluation of hundreds of intermediate pre-training checkpoints from large language models, we demonstrate that W2SG is not an innate capability but emerges via a phase transition tightly coupled with the progression of pre-training.

cs.LG↗
arXiv2026

FAB: A First-Order AB-based Gradient Algorithm for Distributed Bilevel Optimization over Time-Varying Directed Graphs

Distributed optimization over time-varying directed graphs has shown promising performance in addressing challenges posed by complex communication constraints in real-world scenarios. In many practical settings, however, the direct application of distributed optimization algorithms encounters additional difficulties, most notably hyperparameter tuning, which our empirical observations suggest can be effectively mitigated by integrating bilevel optimization. Motivated by these findings, we study distributed bilevel optimization over time-varying directed networks, a problem that remains largely unexplored due to the compounded challenges arising from consensus bias in dynamic unbalanced communication and the nested optimization structure. In this work, we propose a fully first-order distributed gradient-based algorithm that integrates the Push-Pull (also known as AB) communication strategy with a value function-based penalty method and establish its non-asymptotic convergence properties. Notably, a simplified variant of our analysis framework for nonconvex single-level distributed optimization establishes a convergence rate for the Push-Pull algorithm, thereby resolving an open question concerning its convergence over time-varying directed graphs. Empirical evaluations across diverse tasks, including hyperparameter tuning, data hyper-cleaning, and reinforcement learning, validate the effectiveness and efficiency of the proposed algorithm.

math.OC↗
arXiv2026

Knowledge-data fusion framework for frequency security assessment in low-inertia power systems

The integration of renewable energy via power electronics is transforming power grids into low-inertia systems, heightening the risks of frequency insecurity and widespread outages. Therefore, frequency security assessment (FSA) methods are urgently needed to ensure the reliable system operation. Recently, knowledge-data fusion models attempt to address the limitations of knowledge-driven (accuracy) and data-driven (generalization) FSA methods. However, current methods remain confined to shallow knowledge-data integration due to challenges in representing heterogeneous knowledge and establishing interactive mechanisms. Here, by classifing FSA domain knowledge into physics-guided and physics-constrained categories, we propose a guided learning-constrained network (GL-CN) framework, which deeply integrates domain knowledge across both network architecture and training process. In this framework, a data-driven model with dual input channels combining graph convolutional networks (GCN) and multilayer perceptrons (MLP) is proposed to extract both nodal and system-level power system features. Furthermore, guided learning enhances model generalization through data augmentation in pre-training utilizing physics-guided knowledge, while constrained network encodes physics-constrained knowledge into the network architecture and loss function to ensure physics-consistent and robust predictions. Validated on Yunnan Provincial Power Grid in China, our method reduces FSA time from days to seconds compared to traditional simulation, achieving 98% accuracy, robustness against 39.0% knowledge error, and generalization for 40%-60% renewable penetration. This provides a solid solution for mitigating blackouts caused by frequency insecurity and offers a generalizable paradigm for broader cross-domain problems.

eess.SY↗
arXiv2026

Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use, particularly in search-based settings that require multi-turn reasoning and knowledge acquisition. However, existing approaches typically rely on outcome-based rewards that are only provided exclusively upon generating the final answer. This reward sparsity becomes particularly problematic in multi-turn settings, where long trajectories exacerbate three critical issues: (i) advantage collapse, where all rollouts receive identical rewards and provide no useful learning signals; (ii) lack of fine-grained credit assignment, where the correctness of intermediate turns is obscured, especially in long-horizon tasks; and (iii) poor sample efficiency, where each rollout yields only a single outcome signal, leading to low data utilization. In this paper, we propose Information Gain-based Policy Optimization (IGPO), a simple yet effective RL framework that provides dense and intrinsic supervision for multi-turn agent training. IGPO models each interaction turn as an incremental process of acquiring information about the ground truth, and defines turn-level rewards as the marginal increase in the policy's probability of producing the correct answer. Unlike prior process-level reward approaches that depend on external reward models or costly Monte Carlo estimation, IGPO derives intrinsic rewards directly from the model's own belief updates. These intrinsic turn-level rewards are combined with outcome-level supervision to form dense reward signals. Extensive experiments on both in-domain and out-of-domain benchmarks demonstrate that IGPO consistently outperforms strong baselines in multi-turn scenarios, achieving higher accuracy and improved data efficiency. Our code is available at https://github.com/GuoqingWang1/IGPO.

cs.CL↗
arXiv2026

SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity

While stochastic bilevel optimization methods have been extensively studied for addressing large-scale nested optimization problems in machine learning, it remains an open question whether the optimal complexity bounds for solving bilevel optimization are the same as those in single-level optimization. Our main result resolves this question: SPABA, an adaptation of the PAGE method for nonconvex optimization in (Li et al., 2021) to the bilevel setting, can achieve optimal sample complexity in both the finite-sum and expectation settings. We show the optimality of SPABA by proving that there is no gap in complexity analysis between stochastic bilevel and single-level optimization when implementing PAGE. Notably, as indicated by the results of (Dagréou et al., 2022), there might exist a gap in complexity analysis when implementing other stochastic gradient estimators, like SGD and SAGA. In addition to SPABA, we propose several other single-loop stochastic bilevel algorithms, that either match or improve the state-of-the-art sample complexity results, leveraging our convergence rate and complexity analysis. Numerical experiments demonstrate the superior practical performance of the proposed methods.

math.OC↗
arXiv2026

Beyond the Black Box: A Survey on the Theory and Mechanism of Large Language Models

The rapid emergence of Large Language Models (LLMs) has precipitated a profound paradigm shift in Artificial Intelligence, delivering monumental engineering successes that increasingly impact modern society. However, a critical paradox persists within the current field: despite the empirical efficacy, our theoretical understanding of LLMs remains disproportionately nascent, forcing these systems to be treated largely as ``black boxes''. To address this theoretical fragmentation, this survey proposes a unified lifecycle-based taxonomy that organizes the research landscape into six distinct stages: Data Preparation, Model Preparation, Training, Alignment, Inference, and Evaluation. Within this framework, we provide a systematic review of the foundational theories and internal mechanisms driving LLM performance. Specifically, we analyze core theoretical issues such as the mathematical justification for data mixtures, the representational limits of various architectures, and the optimization dynamics of alignment algorithms. Moving beyond current best practices, we identify critical frontier challenges, including the theoretical limits of synthetic data self-improvement, the mathematical bounds of safety guarantees, and the mechanistic origins of emergent intelligence. By connecting empirical observations with rigorous scientific inquiry, this work provides a structured roadmap for transitioning LLM development from engineering heuristics toward a principled scientific discipline.

cs.CL↗
arXiv2026

A Unified Framework for 2D Nonseparable Fractional Fourier Transform: From Geometric Completeness to Applications

The one-dimensional (1D) fractional Fourier transform (FRFT) generalizes the Fourier transform, offering significant advantages in the time-frequency analysis of non-stationary signals. While various 2D extensions exist, such as the 2D separable FRFT (SFRFT), gyrator transform (GT), coupled FRFT (CFRFT), and earlier nonseparable definitions, they suffer from fragmented theoretical frameworks and a fundamental lack of geometric consistency with the 2D Wigner distribution (WD). Addressing these limitations, we propose a unified 2D nonseparable FRFT (NSFRFT) framework. Theoretically derived from the intersection of the symplectic and special orthogonal groups (isomorphic to the unitary group $\mathrm{U}(2)$), this transform inherently possesses four degrees of freedom and mathematically incorporates the 2D SFRFT, GT, and CFRFT as special cases. Unlike prior algebraic generalizations, it strictly preserves the rigid 4D rotational geometry of the 2D WD, ensuring geometric consistency and numerical stability. We derive its essential properties and develop efficient discrete algorithms with a computational complexity of $O(N^{2}\log N)$. Numerical simulations validate the superiority of the 2D NSFRFT in analyzing coupled chirp signals and demonstrate its robustness in filtering and image encryption and decryption applications.

eess.SP↗