arXiv subjects

Bin Yang

Publications and source records attributed to Bin Yang.

At least 19 recordsLinked to original sources

arXiv2026

Anti-Localization Uplink Communications in Satellite-Terrestrial Systems

This paper investigates the anti-localization uplink communication in a satellite-terrestrial system, where a ground transmitter Alice communicates with a legitimate satellite receiver Bob in the presence of multiple cooperative adversarial satellites attempting to localize Alice with the time difference of arrival (TDOA) technique. Specifically, we propose a cooperative jamming-based scheme for such anti-localization communication,in which Alice exploits the superposition coding with power allocation to simultaneously transmit information/jamming signals for communication with Bob and for confusing signal detection/TDOA measurement at adversarial satellites, while Bob employs the combining vector technique to enhance the desired information signal and also suppress the jamming. We define a localization error probability (LEP) metric to jointly depict both the impacts of signal detection and TDOA measurement on localization performance, and then develop a theoretical framework for the LEP modeling under the proposed scheme. We further explore the joint optimal design of jamming coding and power for LEP maximization, subject to the constraints of AliceBob communication reliability and Alice's transmit power. An effective sample average approximation method is also provided to tackle this non-convex optimization problem. Finally, extensive numerical results are illustrated to validate our theoretical models and demonstrate how the cooperative jamming helps to provide an anti-localization guarantee while ensuring communication reliability

cs.CR↗

arXiv2026

WPBench: A Comprehensive Benchmark for Wind Power Forecasting

Accurate, reliable, and deployable wind power forecasting is critical for power system dispatch, renewable energy integration, and electricity market operations. Progress in this field hinges on the ability to empirically and comprehensively benchmark forecasting methods. Yet existing benchmarks fall short of supporting systematic evaluation in four key aspects: 1) limited coverage of wind power scenarios across turbine scale, variable composition, and spatial structure; 2) incomplete coverage of forecasting model families; 3) evaluation metrics misaligned with wind power requirements; and 4) limited structure-aware diagnostics beyond individual temporal patterns. To address these limitations, we propose WPBench, a comprehensive, fair, and extensible benchmark for wind power forecasting. WPBench integrates 26 public datasets organized by turbine scale and variable composition, spanning single-turbine, multi-turbine, univariate, and multivariate settings. Under unified processing, training, and evaluation protocols, it benchmarks 19 representative models covering traditional methods, deep temporal models, spatio-temporal models, and foundation models. Beyond point-wise errors, WPBench assesses forecast-curve fidelity and computational efficiency, and delivers structure-aware diagnostics across temporal, variable-dependency, and spatial-dependency perspectives. Together, these capabilities enable systematic model comparison across diverse wind scenarios and provide a reusable platform for future research.

cs.LG↗

arXiv2026

QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization

Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids. Recently, training foundation models on massive datasets to achieve accurate zero-shot forecasting has emerged as a major research focus. However, current studies predominantly prioritize architectural innovations while insufficiently addressing data diversity, often relying on simple data sampling strategies that fail to manage complex data distributions effectively, leading to inefficient use of training data and suboptimal performance. To address this, we propose QUALS, a large-scale time series corpus equilibrium framework. QUALS significantly enhances data efficiency, i.e., enabling existing models to achieve superior performance using only a small fraction of the original training data. Specifically, QUALS operates through two core mechanisms. First, a pattern quantization framework systematically decodes heterogeneous patterns from mixed corpora via vector quantization and uniform binning. Second, a learnability synchronization framework calibrates sampling weights for heterogeneous patterns, bridging the optimization gap between simple and complex motifs to maximize overall training efficiency. Extensive benchmarks demonstrate that pre-training on QUALS consistently achieves superior zero-shot performance, even under substantially reduced training budgets.

cs.LG↗

arXiv2026

BLINC: Blind Calibration For Training-Free Speech Enhancement Adaptation

Speech enhancement (SE) models degrade under domain shifts and have to adapt to unseen target domains during deployment. Most existing test-time adaptation (TTA) methods for SE do so by adapting a subset of the model weights using a self-supervised loss, which requires backpropagation at test-time and permanently alters the model. We instead recalibrate the prediction itself and propose BLINC, a training-free TTA method that remaps the predicted time-frequency mask onto a bimodal target distribution by histogram matching. At test-time, the target distribution is parameterized from blind features of the noisy recording, so neither a reference distribution from a classical algorithm nor online metric optimization is involved. BLINC improves the overall quality of both evaluated SE models on almost every target condition and matches or exceeds the loss-based TTA baselines at minimal overhead.

eess.AS↗

arXiv2026

A Unified Framework for Wasserstein Convergence of ULMC Methods beyond Log-Concavity: Old and New

As a fundamental task across computational statistics, scientific computing and machine learning, sampling from high-dimensional probability distributions has received increasing attention in recent years. Numerous sampling algorithms have been proposed, among which underdamped Langevin Monte Carlo (ULMC) methods based on underdamped Langevin dynamics (ULD) have emerged as a class of efficient ones. In this work, we introduce a ``universal" predictor-corrector formulation that bridges Euler-type, UBU-type and randomized schemes through different choices of method parameters. Notably, the ``universal" integrator induces two novel classes of low-cost integrators, termed low-cost randomized integrators (LC-RIs) and low-cost UBU integrators (LC-UBUIs), as well as their exponential-free variants based on polynomial and rational approximations. The resulting new UBU-type and randomized schemes require only one gradient evaluation and two Gaussians per iteration, considerably reducing the number of gradient evaluations or Gaussians per iteration required by existing counterparts. Further, a general framework of long-time error analysis is developed for general discretization schemes in a probability metric. Under certain smoothness and non-log-concavity conditions, we rely on the unified framework to establish non-asymptotic $\mathcal{W}_1$-error bounds of both old and new schemes, revealing convergence rates of order $\mathcal{O}(d^{\frac{1}{2}}h)$ for Euler-type schemes, order $\mathcal{O}(d h^2)$ for UBU-type ones and order $\mathcal{O}(d^{\frac{1}{2}}h^{\frac{3}{2}})$ for randomized ones. In the strongly convex setting, the same non-asymptotic error bounds can be recovered in $\mathcal{W}_2$-distance. Numerical experiments corroborate the theoretical findings.

math.NA↗

arXiv2026

Existence of pullback $\mathcal{D}$-attractors for Kirchhoff wave equations with strong damping and delay

This paper studies the existence of pullback $\mathcal{D}$-attractors for non-autonomous Kirchhoff wave equations with strong damping and delay effects in the phase space $\mathcal{E} = C_{H^1_0(Ω)} \times C_{L^2(Ω)}$. The model contains a strong damping term $-Δ\partial_t u$, a nonlocal Kirchhoff term $Ψ(\|\nabla u\|^2)$, a state-dependent delay term $ϕ(t, u_t)$, and a time-dependent external force $h(x, t)$. There appear to be no results on the pullback attractors of Kirchhoff wave equations involving both strong damping and delay effects in the literature. To this end, we establish delicate uniform estimates and employ the contraction function method to prove the pullback asymptotic compactness of the associated process, which yields the existence of pullback $\mathcal{D}$-attractors.

math.AP↗

arXiv2026

Pullback Attractors for a Non-Autonomous Plate System with Strong Damping and Delay

This paper addresses the existence of pullback attractors for a class of nonlinear non-autonomous strongly damped plate equations with delay. The model contains the biharmonic operator, the strong damping term, a nonlinear source term and a delay operator acting on the history of the solution. The interaction between the strong damping mechanism and the hereditary delay effect gives rise to several analytical difficulties in deriving uniform estimates and proving pullback asymptotic compactness. To overcome these difficulties, we construct a modified energy functional adapted to the strong damping structure and employ the contractive function method to handle the delay term in the history phase space. By establishing the existence and uniqueness of weak solutions, uniform pullback estimates and the pullback asymptotic compactness of the associated non-autonomous process, we prove the existence of pullback attractors for the strongly damped plate equation with delay.

math.AP↗

arXiv2026

When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning

Urban region representation learning commonly combines heterogeneous data sources, such as mobility flows, points of interest, and land-use information, to support tasks including mobility analysis, public safety forecasting, and service demand estimation. Existing multi-view methods typically improve region embeddings by strengthening interactions across views. However, such methods often overlook view-specific regional structures and may propagate correlations induced by shared latent factors, which can reduce the stability of downstream predictions. To overcome this major limitation, we propose CURE, a confounder-aware framework for multi-view urban region representation learning. CURE first encodes each view with its regional graph structure, estimates a shared latent component, and then reduces its projected influence before cross-view interaction. A hierarchical graph-aware fusion module subsequently aggregates the residual view representations using local and global regional contexts Experiments on three real-world cities show that CURE improves predictive performance, remains robust under missing and noisy input views, and provides reliable cross-view integration through shared component separation and context-dependent view weighting.

cs.LG↗

arXiv2026

Breaking the Duplex Barrier: Lane-Granularity OCS Scheduling for LLM Training

Optical circuit switch (OCS) can reconfigure physical connectivity to match the predictable communication schedules of large language model (LLM) training. Although each OCS light path is physically simplex, existing demand-aware OCS schedulers allocate capacity in duplex-port pairs, forcing equal bandwidth in both directions and stranding capacity under asymmetric node-pair traffic. This paper present LACE, the first offline OCS schedule compiler that independently allocates transmit (TX) and receive (RX) lanes for LLM training. Without changing the selected collective algorithms, operation order, or rank placement, LACE reconstructs directed node-level demand, jointly determines which consecutive operations share a configuration and how many simplex circuits serve each direction, and realizes these allocations as physical lane bindings and optical paths under per-node lane-inventory and multi-OCS fabric constraints. Software acknowledgments carry feedback over independently provisioned return paths, while coordinated link configuration and recovery verify each configuration before communication resumes. On a separate three-server testbed using fixed topologies and matched per-port rate limits, LACE's asymmetric connectivity achieves $1.80\times$ speedup for communication replay and $1.27\times$ for GPT-2 training over a symmetric-topology baseline. At larger scale, simulations of LLaMA-3.1 70B and 405B schedules with sixteen 400-Gb/s ports per server show that LACE achieves $1.21$--$2.04\times$ communication speedup over the latest duplex OCS scheduler.

cs.NI↗

arXiv2026

Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds

Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across augmented views or by masked scene modeling. However, the resulting representations transfer poorly to instance localization, and often require full finetuning for strong performance. Instance awareness is a fundamental component of 3D perception, thus bridging this gap is crucial for progressing toward true 3D foundation models that support all downstream tasks on 3D data. In this work, we introduce PointINS, an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning. PointINS employs an orthogonal offset branch to jointly learn high-level semantic understanding and geometric reasoning, yielding instance awareness. We identify two consistent properties essential for robust instance localization and formulate them as complementary regularization strategies, Offset Distribution Regularization (ODR), which aligns predicted offsets with empirically observed geometric priors, and Spatial Clustering Regularization (SCR), which enforces local coherence by regularizing offsets with pseudo-instance masks. Through extensive experiments across five datasets, PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation, paving the way for scalable 3D foundation models.

cs.CV↗

arXiv2026

The Non-Principal-Axis Rotation and Convex Shape Model of Earth Quasi-Satellite and the Target of China's Tianwen-2 Mission (469219) Kamo`oalewa

(469219) Kamo`oalewa is the most stable Earth quasi-satellite and the target of China's Tianwen-2 asteroid sample return mission. Due to its small size, fast rotation, and the limited observing geometry accessible from the ground, many physical properties of Kamo`oalewa remain poorly constrained, including the rotational state and shape. We obtained three epochs of high-cadence, high signal-to-noise photometric lightcurves of Kamo`oalewa with the Gemini North Telescope from 2026 April to May, supplemented by one lightcurve from the Lowell Discovery Telescope in 2026 May. Our analysis suggests that Kamo`oalewa is in a non-principal-axis rotation with an elongated shape. Four possible solutions exist, including a long-axis mode (LAM) solution and a short-axis mode (SAM) solution, as well as their corresponding mirrored angular momentum directions. The most preferable solution has a LAM model with a precession period $P_ϕ=27.65\pm0.03~\text{min}$ and a rotational period $P_ψ=50.49\pm0.08~\text{min}$, and the angular momentum points to ecliptic coordinates $(λ, β) = (226^\mathrm{o}\pm20^\mathrm{o}, -39^\mathrm{o}\pm20\mathrm{o})$, although we cannot rule out other solutions or other close-by periods due to aliasing. We also derived a convex shape inversion for the LAM models with consistent rotational parameters but could not find a satisfactory inversion for the SAM models. The corresponding angular momentum points to $(λ, β)=(225^\mathrm{o}, -43^\mathrm{o})$, and the periods are $P_ϕ=27.90~\text{min}$ and $P_ψ=49.66~\text{min}$. The non-principal-axis rotation provides additional constraints on the dynamic history or the internal structure of Kamo`oalewa.

astro-ph.EP↗

arXiv2026

DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version

Due to the proliferation of vehicle trajectory data enabled by advanced sensing technologies, path representation learning has become a pivotal task in intelligent transportation systems. Although existing self-supervised approaches have achieved promising performance, their dependence on deterministic contrastive learning paradigms and handcrafted view augmentation strategies inherently restricts their cross-scenario generalization capabilities. To address these limitations, we present DGCPath, an innovative Distribution-aware Generative Contrastive learning framework for Path representation. This framework establishes a synergistic connection between generative modeling and distributional contrastive learning, enabling the acquisition of robust and transferable feature embeddings. Specifically, our framework incorporates: (1) a diffusion-based view generator that autonomously produces semantically coherent yet diverse trajectory views from Gaussian noise; (2) a variational contrastive mechanism that enforces latent feature alignment at the distribution level, transcending conventional instance-wise consistency; and (3) a novel generative cross-supervision module that reinforces view-level consistency through cross-view reconstruction learning. Comprehensive evaluations on three real-world trajectory datasets demonstrate that DGCPath outperforms state-of-the-art baselines on two distinct downstream tasks, validating its enhanced generalization capability and representation effectiveness.

cs.AI↗

arXiv2026

REFINE: Trajectory Representation Learning via Closed-Loop Transcription -- Extended Version

Trajectory representation learning underpins a wide range of trajectory analytics tasks; however, most existing self-supervised approaches, whether discriminative or generative, adopt an open-loop paradigm, relying on fixed data augmentations or random masking without feedback, which limits their ability to generalize and scale. We propose REFINE, a simple yet effective Representation lEarning Framework vIa closed-loop traNscription rEfinement for trajectory data. Drawing upon feedback control theory, REFINE tightly couples road-network-aware generative reconstruction with feedback-driven contrastive learning, enabling the model to capture fine-grained local movement semantics and global spatio-temporal dependencies without manually designed augmentation views. We further provide a control-theoretic analysis that establishes convergence guarantees for the proposed closed-loop optimization. Extensive experiments on four real-world datasets demonstrate that REFINE consistently outperforms state-of-the-art methods across multiple downstream tasks while remaining computationally efficient and scalable. This paper is an extended version of REFINE: Trajectory Representation Learning via Closed-Loop Transcription, to appear in KDD 2026.

cs.LG↗

arXiv2026

TDLight: A Framework for Incremental Light-Curve Management and Continuous Classification Optimization

Time-series observations of celestial objects are fundamental to studying variable and transient phenomena. As time-domain surveys continue to scale up, timely automated classification is essential for rapid follow-up. Many existing approaches treat storage and analysis as separate stages, archiving data first and analyzing it later. Yet each source is a continuously growing stream, and early observations often contain sufficient information to assign scientifically useful labels before the full light curve is available. Motivated by this, we present TDLight, a framework for light-curve management and trigger-based classification over incremental data streams. Built on the time-series database TDengine, the system loads the Gaia DR2 archive (approximately 4.8 x 10^7 rows) in 33 s and supports low-latency retrieval. As new observations accumulate, TDLight automatically triggers a lightweight LightGBM-based classification pipeline that requires no GPU. When prediction confidence exceeds a predefined threshold, these early results are written back to the database, providing reliable classifications before offline analysis is complete. The deployed system also supports manual label confirmation and optional incremental training. Evaluated on the LEAVES dataset (approximately 1.10 million sources spanning 10 classes), the system achieves an overall accuracy of 93.6% and a weighted F1 score of 93.7%. Furthermore, it identifies 560 high-confidence catalog-disagreement candidates for follow-up verification. Notably, this includes correcting 150 RRc variables erroneously labeled as EW binaries due to inherited period-doubling artifacts. TDLight and the related data products are publicly available.

astro-ph.IM↗

arXiv2026

Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents

Reinforcement learning is a natural way to post-train LLM agents for long-horizon interactive tasks judged only by end-of-task verification, yet a shared belief holds that outcome-only RL soon hits a ceiling on small open models. Recent work therefore compensates around the training with denser rewards, SFT priors, skill libraries, curated memory, or multi-agent orchestration. We argue the ceiling is an artifact of two failures of common practice. Signal starvation: group-relative RL with sparse outcome-only rewards yields a gradient only when a task's rollout group mixes successes and failures, so under-scaled exploration silences exactly the hardest, most instructive tasks. Policy drift: squeezing many updates out of a small task pool degrades the policy itself, as an unanchored objective lets the sampling distribution collapse exactly when saturation has already made informative groups rare. We present CANOPY (Coverage-ANchored On-PolicY RL), a minimalist protocol attacking both directly: scale same-task exploration until the natural signal reappears, keep every update on-policy, KL-anchored, and confined to the agent's own action tokens, then cash in an enlarged interaction budget at test time. On AppWorld, a long-horizon interactive coding benchmark, a Qwen3-14B policy trained with CANOPY through environment interaction alone--without task-specific supervision, auxiliary credit signals, or elaborate agent scaffolding--topped the public leaderboard (Feb. 2026; Test-Normal TGC 86.9, Test-Challenge 67.6), and the same design principles lift Qwen3.5-9B on SWE-bench Verified by 16.6 points. Agentic RL alone thus internalizes long-horizon capability directly into a small open model; we plan to release the complete training stack at https://github.com/AlibabaResearch/SignalCoverageRL.

cs.LG↗

arXiv2026

ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies

LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolving'' MAS, treated as a more flexible and powerful technical route, can construct task-adaptive workflows or communication topologies, instead of relying on a predefined static structue template. Current self-evolving MAS mainly focus on Spatial Evolving or Temporal Evolving paradigm, which only considers the single dimension of evolution and does not fully incentivize LLMs' collaborative capability. In this work, we start from a novel Spatio-Temporal perspective by proposing ST-EVO, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler. To make precise Spatio-Temporal scheduling, ST-EVO can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience. Extensive experiments on nine benchmarks demonstrate the state-of-the-art performance of ST-EVO, achieving about 5%--25% accuracy improvement.

cs.MA↗

arXiv2026

TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking

Query denoising has become a standard training strategy for DETR-based detectors. Denoising queries, initialized by perturbing ground truths, share similarities with track queries in a typical DETR-based Multi-Object Tracking (MOT) method, warranting exploration of their potential synergy. However, query denoising in existing MOT methods is performed only within a single frame, preventing trackers from learning inter-frame temporal association from the denoising process. To address this issue, we propose TQD-Track, a Temporal Query Denoising (TQD) method tailored for MOT. In our method, denoising queries are initialized from ground truths in the previous frame and then propagated into the current frame in the same way as track queries, serving as additional independent data association candidates. These denoising queries carry temporal information and instance-specific feature representations, effectively emulating and augmenting track queries. Moreover, to simulate various real-world MOT challenges for robust tracking, we introduce several corresponding noise types to generate diverse denoising queries. We analyze the impact of our temporal query denoising for two tracking paradigms, tracking-by-attention and alternating detection and association, demonstrating its generalization. Extensive experiments on the nuScenes and Argoverse~2 datasets demonstrate that our approach consistently enhances different MOT baselines, requiring only modifications in the training process. Code and models are available at https://github.com/yutongy98/TQD-Track.

cs.CV↗

arXiv2026

Super-Resolution of Range-Doppler Maps: A Case Study with Chirp-Sequence Radar and Transformer

Range-Doppler (rD) maps produced by chirp- sequence (CS) radar systems are fundamentally limited in reso- lution by bandwidth, carrier frequency, and coherent processing interval constraints. Improving resolution through hardware is often impractical due to regulatory, cost, and real-time operation requirements. In this work, we investigate deep learning-based super- resolution of rD maps in both range and Doppler using a real- world dataset collected with an Infineon millimeter-wave CS radar. We propose a memory-efficient transformer architecture based on dual-path shifted window (DPSWIN) attention, which combines axial/dual-path attention with 1D shifted window (SWIN) attention for scalable processing of high-dimensional radar data. Our model is benchmarked against existing 2D SWIN attention-based super-resolution models, which we adapt to the rD-map super-resolution task. We prioritize reconstruction fidelity over perceptual quality and employ root mean squared error (RMSE)-based training objectives. We avoid adversarial or perceptual losses that may introduce visually plausible but physically incorrect structures. In addition, we incorporate CFAR-based target-detection losses to optimize downstream target detectability in the super-resolved rD maps. We further study the impact of signal processing and training design choices on the super-resolution, including magnitude compression, spatial upsampling strategies, and loss formulations. Experimental results demonstrate that the proposed framework achieves computationally efficient rD map super-resolution on previously unseen real-world environments.

eess.SP↗