arXiv subjects

Yin Tang

Publications and source records attributed to Yin Tang.

At least 19 recordsLinked to original sources

arXiv2026

FreqNav: Stage-Wise Frequency Routing for Object-Oriented Aerial Vision-Language Navigation

Object-oriented aerial vision-and-language navigation (VLN) requires searching for a described target and landing on it precisely, under long-horizon and closed-loop control. Guided by a target-descriptive instruction during navigation, perceptual priorities dynamically evolve: early-stage exploration prioritizes low-frequency spatial layout, and then shifts to high-frequency target details. Existing VLN methods model the varying perceptual requirements across navigation stages with identical visual tokens, leading to interference from irrelevant objects and background clutter. To this end, we therefore formulate long-horizon aerial navigation as a frequencypreference shift from spatial structure to local detail and propose FreqNav, a lightweight frequency-routing adaptive perception framework. Under a fixed computational budget, FreqNav dynamically reallocates visual tokens across frequency components according to the current navigation stage. A Frequency Token Router selects stage-relevant visual representations from dual-view observations, while a Phase-dependent Grounding Module anchors visual evidence through explicit supervision. A Diffusion Transformer then predicts smooth trajectories for continuous control. Experiments show that FreqNav outperforms strong baselines while achieving approximately 3x faster inference. Real-world deployment further demonstrates its effectiveness, efficiency, and practical potential for long-horizon aerial autonomy.

cs.RO↗

arXiv2026

Complex Conformal Manifolds

Complex conformal field theories (CFTs) have recently emerged as essential frameworks for understanding non-Hermitian criticality, weakly first-order phase transitions, and walking renormalization group flows, while their general structures remain largely unknown. In this work, we propose a systematic construction of complex CFTs by analytically continuing exactly marginal couplings into the complex plane. This procedure applies uniformly to bulk, boundary, and defect deformations, preserving conformal symmetry while generically complexifying operator spectra and other universal data. Using the compact free boson as a solvable laboratory, we uncover the global structure of the complexified Gaussian conformal manifold. More generally, we demonstrate that genuinely complex rational CFTs do not exist: rational points remain confined to the real regime, providing a sharp distinction between real and complex theories. In the defect case, we investigate the one-parameter family of conformal defects in the Ising CFT and derive exact expressions for the defect spectrum, energy transmission coefficient, and effective central charge from analytic continuation. The theoretical predictions are precisely verified in non-Hermitian critical Ising and free fermion chains using bulk-defect correlators, entanglement entropy, and complex energy transport, providing concrete evidence for the complex defect conformal manifold. Finally, we study complex boundary renormalization-group flows through the AdS/BCFT correspondence. Our results establish complex conformal manifolds as a controlled bridge between solvable lattice models, complex CFTs, and holography, while providing stringent analytic benchmarks for the nonunitary conformal bootstrap.

hep-th↗

arXiv2026

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

We introduce PerceptionRubrics, a rubric-based evaluation framework that addresses the gap between saturated benchmark scores and real-world brittleness. Shifting evaluation from holistic semantic matching to rigorous atomic auditing, PerceptionRubrics pairs 1,038 information-dense images with over 10,000 instance-specific rubrics. These criteria are derived from golden captions constructed via a novel Circular Peer-Review consensus pipeline and then distilled into a dual-stream system of Must-Right (essential facts) and Easy-Wrong (fine-grained details) rubrics. Crucially, PerceptionRubrics implements a Gated Scoring mechanism: unlike linear averages, failure on mandatory visual facts triggers sharp binary penalties. Extensive evaluation yields critical insights: (1) The Reliability Gap: models often verify fragmented elements correctly yet fail strict conjunctive constraints, exposing brittleness in dense domains; (2) Open-Closed Stratification: contrary to reasoning trends, we reveal a persistent 8% perception deficit between open-source and proprietary frontiers; and (3) Human-Aligned Rigor: our gated metrics substantially out-align conventional benchmarks, validating that strict perceptual fidelity is the prerequisite for reliable generation.

cs.CV↗

arXiv2026

Semiparametric Efficiency of Residual Correlation Testing under Gaussian Additive Noise Models

This paper studies conditional independence testing under the Gaussian additive noise model (GANM), where two variables are modeled as nonlinear functions of covariates with independent bivariate Gaussian regression errors. Under this framework, conditional independence can be characterized by the correlation coefficient of the regression errors, which motivates a test based on the Pearson correlation coefficient computed from the fitted residuals. Despite its simple form, the asymptotic behavior and statistical efficiency of the resulting test have not been well understood. In this paper, we develop the semiparametric efficiency theory under GANM and show, surprisingly, that the efficient estimator coincides exactly with the ordinary residual Pearson correlation estimator. We further establish the asymptotic properties of the proposed test and develop the corresponding inference procedure. Simulation studies demonstrate that the proposed method achieves near-oracle efficiency and competitive empirical power while maintaining valid Type I error control. We further apply the proposed test to conditional dependence analysis of U.S. stock returns.

math.ST↗

arXiv2026

A Reproducing-Kernel-Based Nonparametric Test for Conditional Independence of Functional Data

Conditional independence is a fundamental concept in many areas of statistical research, including, for example, sufficient dimension reduction, causal inference, and statistical graphical models. In many modern applications, data arise in the form of random functions, making it important to determine whether two random functions are conditionally independent given a third. However, to the best of our knowledge, existing conditional independence tests in the literature apply only to multivariate data, and extensions to the functional setting are not available. To fill this gap, we develop a reproducing-kernel-based test for conditional independence of random functions based on the conjoined conditional covariance operator (CCCO). We rigorously derive the asymptotic distribution of the CCCO estimator using a recently established sharpened convergence rate for the regression operator (Choi et al., 2026). Based on this result, we construct a test statistic using the spectral decomposition of the operator appearing in the asymptotic distribution. The proposed method is illustrated through applications to an activity and biometrics dataset and a macroeconomic dataset.

stat.ME↗

arXiv2026

On Sharpened Convergence Rate of Generalized Sliced Inverse Regression for Nonlinear Sufficient Dimension Reduction

Generalized Sliced Inverse Regression (GSIR) is one of the most important methods for nonlinear sufficient dimension reduction. As shown in Li and Song (2017), it enjoys a convergence rate that is independent of the dimension of the predictor, thus avoiding the curse of dimensionality. In this paper we establish an improved convergence rate of GSIR under additional mild eigenvalue decay rate and smoothness conditions. Our convergence rate can be made arbitrarily close to $n^{-1/3}$ under appropriate decay rate and smoothness parameters. As a comparison, the rate of Li and Song (2017) is $n^{-1/4}$ under the best conditions. This improvement is significant because, for example, in a semiparametric estimation problem involving an infinite-dimensional nuisance parameter, the convergence rate of the estimator of the nuisance parameter is often required to be faster than $n^{-1/4}$ to guarantee desired semiparametric properties such as asymptotic efficiency. This can be achieved by the improved convergence rate, but not by the original rate. The sharpened convergence rate can also be established for GSIR in more general settings, such as functional sufficient dimension reduction.

math.ST↗

arXiv2026

Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering

Continuous navigation in complex environments is critical for Unmanned Aerial Vehicle (UAV). However, the existing Vision-Language Navigation (VLN) models follow the dead-reckoning, which iteratively updates its position for the next waypoint prediction, and subsequently construct the complete trajectory. Then, such stepwise manner will inevitably lead to accumulated errors of position over time, resulting in misalignment between internal belief and objective coordinates, which is known as "state drift" and ultimately compromises the full trajectory prediction. Drawing inspiration from classical control theory, we propose to correct for errors by formulating such sequential prediction as a recursive Bayesian state estimation problem. In this paper, we design NeuroKalman, a novel framework that decouples navigation into two complementary processes: a Prior Prediction, based on motion dynamics and a Likelihood Correction, from historical observation. We first mathematically associate Kernel Density Estimation of the measurement likelihood with the attention-based retrieval mechanism, which then allows the system to rectify the latent representation using retrieved historical anchors without gradient updates. Comprehensive experiments on TravelUAV benchmark demonstrate that, with only 10% of the training data fine-tuning, our method clearly outperforms strong baselines and regulates drift accumulation.

cs.RO↗

arXiv2025

Emergence of 3D Superconformal Ising Criticality on the Fuzzy Sphere

Supersymmetric conformal field theories (SCFTs) form a unique subset of quantum field theories which provide powerful insights into strongly coupled critical phenomena. Here, we present a microscopic and non-perturbative realization of the three-dimensional $\mathcal{N}=1$ superconformal Ising critical point, based on a Yukawa-type coupling between a 3D Ising CFT and a gauged Majorana fermion. Using the recently developed fuzzy sphere regularization, we directly extract the scaling dimensions of low-lying operators via the state-operator correspondence. At the critical point, we demonstrate conformal multiplet structure together with the hallmark of emergent spacetime supersymmetry through characteristic relations between fermionic and bosonic operators. Moreover, by tuning the Yukawa coupling, we explicitly track the evolution of operator spectra from the decoupled Ising-Majorana fixed point to the interacting superconformal fixed point, revealing renormalization-group flow at the operator level. Our results establish a controlled, non-perturbative microscopic route to 3D SCFTs.

cond-mat.str-el↗

arXiv2025

Boundary Criticality of Complex Conformal Field Theory: A Case Study in the Non-Hermitian 5-State Potts Model

Conformal fields with boundaries give rise to rich critical phenomena that can reveal information about the underlying conformality. While most existing studies focus on Hermitian systems, here we explore boundary critical phenomena in a non-Hermitian quantum 5-state Potts model which exhibits complex conformality in the bulk. We identify free, fixed and mixed conformal boundary conditions and observe the conformal tower structure of energy spectra, supporting the emergence of conformal boundary criticality. We also studied the duality relation between different conformal boundary conditions under the Kramers-Wannier transformation. These findings should facilitate a comprehensive understanding for complex CFTs and stimulate further exploration on the boundary critical phenomena within non-Hermitian strongly-correlated systems.

cond-mat.stat-mech↗

arXiv2025

A KL-divergence based test for elliptical distribution

We conduct a KL-divergence based procedure for testing elliptical distributions. The procedure simultaneously takes into account the two defining properties of an elliptically distributed random vector: independence between length and direction, and uniform distribution of the direction. The test statistic is constructed based on the $k$ nearest neighbors ($k$NN) method, and two cases are considered where the mean vector and covariance matrix are known and unknown. First-order asymptotic properties of the test statistic are rigorously established by creatively utilizing sample splitting, truncation and transformation between Euclidean space and unit sphere, while avoiding assuming Fr\'echet differentiability of any functionals. Debiasing and variance inflation are further proposed to treat the degeneration of the influence function. Numerical implementations suggest better size and power performance than the state of the art procedures.

stat.ME↗

arXiv2025

Complier General Causal Effect in Randomized Controlled Trials with One-Sided Noncompliance

A randomized controlled trial (RCT) is widely regarded as the gold standard for assessing the causal effect of a treatment or intervention, assuming perfect implementation. In practice, however, randomization can be compromised for various reasons, such as one-sided noncompliance. In this paper, we first systematically study the likelihood-based identifiability in an RCT with one-sided noncompliance. This foundational analysis naturally gives rise to the complier general causal effect (CGCE) as the primary estimand. We further develop two estimators for the CGCE: a simple estimator that requires no nonparametric procedures, and an efficient estimator that achieves the semiparametric efficiency bound. Our theoretical analysis shows that, achieving semiparametric efficiency requires only the nuisance estimators to converge in $L_2$-norm, with no restriction on their convergence rates. This rate-free property opens the door to employing many more modern machine learning methods while still guaranteeing efficiency. Comprehensive simulation studies and a real data application are conducted to illustrate the proposed methods and to compare them with existing approaches.

stat.ME↗

arXiv2025

From Bias to Behavior: Learning Bull-Bear Market Dynamics with Contrastive Modeling

Financial markets exhibit highly dynamic and complex behaviors shaped by both historical price trajectories and exogenous narratives, such as news, policy interpretations, and social media sentiment. The heterogeneity in these data and the diverse insight of investors introduce biases that complicate the modeling of market dynamics. Unlike prior work, this paper explores the potential of bull and bear regimes in investor-driven market dynamics. Through empirical analysis on real-world financial datasets, we uncover a dynamic relationship between bias variation and behavioral adaptation, which enhances trend prediction under evolving market conditions. To model this mechanism, we propose the Bias to Behavior from Bull-Bear Dynamics model (B4), a unified framework that jointly embeds temporal price sequences and external contextual signals into a shared latent space where opposing bull and bear forces naturally emerge, forming the foundation for bias representation. Within this space, an inertial pairing module pairs temporally adjacent samples to preserve momentum, while the dual competition mechanism contrasts bullish and bearish embeddings to capture behavioral divergence. Together, these components allow B4 to model bias-driven asymmetry, behavioral inertia, and market heterogeneity. Experimental results on real-world financial datasets demonstrate that our model not only achieves superior performance in predicting market trends but also provides interpretable insights into the interplay of biases, investor behaviors, and market dynamics.

cs.LG↗

arXiv2025

Does Scaling Law Apply in Time Series Forecasting?

Rapid expansion of model size has emerged as a key challenge in time series forecasting. From early Transformer with tens of megabytes to recent architectures like TimesNet with thousands of megabytes, performance gains have often come at the cost of exponentially increasing parameter counts. But is this scaling truly necessary? To question the applicability of the scaling law in time series forecasting, we propose Alinear, an ultra-lightweight forecasting model that achieves competitive performance using only k-level parameters. We introduce a horizon-aware adaptive decomposition mechanism that dynamically rebalances component emphasis across different forecast lengths, alongside a progressive frequency attenuation strategy that achieves stable prediction in various forecasting horizons without incurring the computational overhead of attention mechanisms. Extensive experiments on seven benchmark datasets demonstrate that Alinear consistently outperforms large-scale models while using less than 1% of their parameters, maintaining strong accuracy across both short and ultra-long forecasting horizons. Moreover, to more fairly evaluate model efficiency, we propose a new parameter-aware evaluation metric that highlights the superiority of ALinear under constrained model budgets. Our analysis reveals that the relative importance of trend and seasonal components varies depending on data characteristics rather than following a fixed pattern, validating the necessity of our adaptive design. This work challenges the prevailing belief that larger models are inherently better and suggests a paradigm shift toward more efficient time series modeling.

cs.LG↗

arXiv2025

Multi-Grained Compositional Visual Clue Learning for Image Intent Recognition

In an era where social media platforms abound, individuals frequently share images that offer insights into their intents and interests, impacting individual life quality and societal stability. Traditional computer vision tasks, such as object detection and semantic segmentation, focus on concrete visual representations, while intent recognition relies more on implicit visual clues. This poses challenges due to the wide variation and subjectivity of such clues, compounded by the problem of intra-class variety in conveying abstract concepts, e.g. "enjoy life". Existing methods seek to solve the problem by manually designing representative features or building prototypes for each class from global features. However, these methods still struggle to deal with the large visual diversity of each intent category. In this paper, we introduce a novel approach named Multi-grained Compositional visual Clue Learning (MCCL) to address these challenges for image intent recognition. Our method leverages the systematic compositionality of human cognition by breaking down intent recognition into visual clue composition and integrating multi-grained features. We adopt class-specific prototypes to alleviate data imbalance. We treat intent recognition as a multi-label classification problem, using a graph convolutional network to infuse prior knowledge through label embedding correlations. Demonstrated by a state-of-the-art performance on the Intentonomy and MDID datasets, our approach advances the accuracy of existing methods while also possessing good interpretability. Our work provides an attempt for future explorations in understanding complex and miscellaneous forms of human expression.

cs.CV↗

arXiv2025

KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse

Recent advances in long-text understanding have pushed the context length of large language models (LLMs) up to one million tokens. It boosts LLMs's accuracy and reasoning capacity but causes exorbitant computational costs and unsatisfactory Time to First Token (TTFT). KV cache reuse, which reuses the exact same KV cache of prefixes and templates or shares similar ones but with extra selective recomputation, offers a promising way to tackle this issue. However, prior studies overlook the cross-request KV reuse and the attention deviations introduced by new tokens during the decoding stage. In this paper, we present a KV cache management module that shares the KV cache across requests under multi-tenant scenarios without sacrificing model accuracy. Our system, KVShare, enables accurate and efficient LLM serving by 1) a Dual-Stage High Deviation algorithm (DHD) that conditionally selects a small portion of KV cache to be recomputed during both prefill and decode phases, and 2) a cache-aware scheduler that prioritizes requests based on their KV cache hit rates and orchestrates continuous batching to achieve enhanced system efficiency and faster TTFT. Multi-task experiments conducted on models such as Qwen2.5-7B,Llama3.1-8B and Yi1.5-9B demonstrate that KVShare reduces TTFT by up to 9.39x and increases 1.2x of the throughput compared to the full KV recompute. Moreover, KVShare achieves 20.38% boost in terms of accuracy compared to SOTA methods.

cs.CL↗

arXiv2025

EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning

Graph Neural Networks (GNNs) have significant advantages in handling non-Euclidean data and have been widely applied across various areas, thus receiving increasing attention in recent years. The framework of GNN models mainly includes the information propagation phase and the aggregation phase, treating nodes and edges as information entities and propagation channels, respectively. However, most existing GNN models face the challenge of disconnection between node and edge feature information, as these models typically treat the learning of edge and node features as independent tasks. To address this limitation, we aim to develop an edge-empowered graph feature preference learning framework that can capture edge embeddings to assist node embeddings. By leveraging the learned multidimensional edge feature matrix, we construct multi-channel filters to more effectively capture accurate node features, thereby obtaining the non-local structural characteristics and fine-grained high-order node features. Specifically, the inclusion of multidimensional edge information enhances the functionality and flexibility of the GNN model, enabling it to handle complex and diverse graph data more effectively. Additionally, integrating relational representation learning into the message passing framework allows graph nodes to receive more useful information, thereby facilitating node representation learning. Finally, experiments on four real-world heterogeneous graphs demonstrate the effectiveness of theproposed model.

cs.LG↗

arXiv2025

Microscopic study of 3D Potts phase transition via Fuzzy Sphere Regularization

The Potts model describes interacting spins with $Q$ different components, which is a direct generalization of the Ising model ($Q=2$). Compared to the existing exact solutions in 2D, the phase transitions and critical phenomena in the 3D Potts model have been less explored. Here, we systematically investigate a quantum $(2+1)$-D Potts model with $Q=3$ using a fuzzy sphere regularization scheme. We first construct a microscopic model capable of achieving a magnetic phase transition that separates a spin $S_3$ permutationally symmetric paramagnet and a spontaneous symmetry-breaking ferromagnet. Importantly, the energy spectrum at the phase transition point exhibits an approximately conformal symmetry, implying that an underlying conformal field theory may govern this transition. Moreover, when tuning along the phase transition line in the mapped phase diagram, we find that the dimension of the subleading $S_3$ singlet operator flows and drifts around the critical value $\sim 3$, which is believed to be crucial for understanding this phase transition, although determining its precise value remains challenging due to the limitations of our finite-size calculations. These findings suggest a discontinuous transition in the 3D 3-state Potts model, characterized by pseudo-critical behavior, which we argue results from a nearby multicritical or complex fixed point.

cond-mat.stat-mech↗

arXiv2024

Belted and Ensembled Neural Network for Linear and Nonlinear Sufficient Dimension Reduction

We introduce a unified, flexible, and easy-to-implement framework of sufficient dimension reduction that can accommodate both linear and nonlinear dimension reduction, and both the conditional distribution and the conditional mean as the targets of estimation. This unified framework is achieved by a specially structured neural network -- the Belted and Ensembled Neural Network (BENN) -- that consists of a narrow latent layer, which we call the belt, and a family of transformations of the response, which we call the ensemble. By strategically placing the belt at different layers of the neural network, we can achieve linear or nonlinear sufficient dimension reduction, and by choosing the appropriate transformation families, we can achieve dimension reduction for the conditional distribution or the conditional mean. Moreover, thanks to the advantage of the neural network, the method is very fast to compute, overcoming a computation bottleneck of the traditional sufficient dimension reduction estimators, which involves the inversion of a matrix of dimension either p or n. We develop the algorithm and convergence rate of our method, compare it with existing sufficient dimension reduction methods, and apply it to two data examples.

stat.ML↗