arXiv subjects

Xingyu Zhou

Publications and source records attributed to Xingyu Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2026

A Control Architecture for Training-Free Memory Use

Prompt-injected memory can improve reasoning without updating model weights, but it also creates a control problem: retrieved content helps only when it is applied in the right state. We study this problem in a strict training-free setting and formulate it as applicability control: when to trigger a memory-assisted second pass, when to trust it, and how to maintain the memory bank over time. Our method combines uncertainty-based routing, confidence-based selective acceptance, bank selection across rule and exemplar memory, and evidence-based governance of the memory bank over time. Under a locked training-free protocol with compute-matched controls, it improves two core arithmetic benchmarks by +7.0 points on SVAMP and +7.67 points on ASDiv over baseline. The same architecture also transfers to QA and agent benchmarks with smaller positive effects and shows the same positive direction on a second checkpoint for the main arithmetic tasks. On arithmetic, the main empirical pattern is that the control architecture, rather than raw memory exposure, drives the improvements on SVAMP and ASDiv. Mechanistically, confidence separates helpful from harmful rule-bank interventions, and under fixed retrieval the repair-versus-corrupt difference localizes to rows whose retrieved set actually contains the edited entries.

cs.AI↗

arXiv2026

Guiding a Diffusion Transformer with the Internal Dynamics of Itself

The diffusion model presents a powerful ability to capture the entire (conditional) data distribution. However, due to the lack of sufficient training and data to learn to cover low-probability areas, the model will be penalized for failing to generate high-quality images corresponding to these areas. To achieve better generation quality, guidance strategies such as classifier free guidance (CFG) can guide the samples to the high-probability areas during the sampling stage. However, the standard CFG often leads to over-simplified or distorted samples. On the other hand, the alternative line of guiding diffusion model with its bad version is limited by carefully designed degradation strategies, extra training and additional sampling steps. In this paper, we proposed a simple yet effective strategy Internal Guidance (IG), which introduces an auxiliary supervision on the intermediate layer during training process and extrapolates the intermediate and deep layer's outputs to obtain generative results during sampling process. This simple strategy yields significant improvements in both training efficiency and generation quality on various baselines. On ImageNet 256x256, SiT-XL/2+IG achieves FID=5.31 and FID=1.75 at 80 and 800 epochs. More impressively, LightningDiT-XL/1+IG achieves FID=1.34 which achieves a large margin between all of these methods. Combined with CFG, LightningDiT-XL/1+IG achieves the current state-of-the-art FID of 1.19.

cs.CV↗

arXiv2026

Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolution

Vector-quantized based models have recently demonstrated strong potential for visual prior modeling. However, existing VQ-based methods simply encode visual features with nearest codebook items and train index predictor with code-level supervision. Due to the richness of visual signal, VQ encoding often leads to large quantization error. Furthermore, training predictor with code-level supervision can not take the final reconstruction errors into consideration, result in sub-optimal prior modeling accuracy. In this paper we address the above two issues and propose a Texture Vector-Quantization and a Reconstruction Aware Prediction strategy. The texture vector-quantization strategy leverages the task character of super-resolution and only introduce codebook to model the prior of missing textures. While the reconstruction aware prediction strategy makes use of the straight-through estimator to directly train index predictor with image-level supervision. Our proposed generative SR model (TVQ&RAP) is able to deliver photo-realistic SR results with small computational cost.

cs.CV↗

arXiv2026

Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models

Latent diffusion models have emerged as the dominant framework for high-fidelity and efficient image generation, owing to their ability to learn diffusion processes in compact latent spaces. However, while previous research has focused primarily on reconstruction accuracy and semantic alignment of the latent space, we observe that another critical factor, robustness to sampling perturbations, also plays a crucial role in determining generation quality. Through empirical and theoretical analyses, we show that the commonly used $β$-VAE-based tokenizers in latent diffusion models, tend to produce overly compact latent manifolds that are highly sensitive to stochastic perturbations during diffusion sampling, leading to visual degradation. To address this issue, we propose a simple yet effective solution that constructs a latent space robust to sampling perturbations while maintaining strong reconstruction fidelity. This is achieved by introducing a Variance Expansion loss that counteracts variance collapse and leverages the adversarial interplay between reconstruction and variance expansion to achieve an adaptive balance that preserves reconstruction accuracy while improving robustness to stochastic sampling. Extensive experiments demonstrate that our approach consistently enhances generation quality across different latent diffusion architectures, confirming that robustness in latent space is a key missing ingredient for stable and faithful diffusion sampling.

cs.CV↗

arXiv2026

Construction of the Global $χ^2$ Function for the Simultaneous Fitting of Correlated Energy-Dependent Cross Sections

In this paper, the global $χ^2$ function for the simultaneous fitting of correlated energy-dependent cross sections is constructed, where the correlations between the measured cross sections of different processes and/or at different center-of-mass energy points, as well as the contributions from the integrated luminosity measurement and the center-of-mass energy measurement, are taken into account.

physics.data-an↗

arXiv2026

Reducing Pilots in Channel Estimation with Predictive Foundation Models

Accurate channel state information (CSI) acquisition is essential for modern wireless systems, which becomes increasingly difficult under large antenna arrays, strict pilot overhead constraints, and diverse deployment environments. Existing artificial intelligence-based solutions often lack robustness and fail to generalize across scenarios. To address this limitation, this paper introduces a predictive-foundation-model-based channel estimation framework that enables accurate, low-overhead, and generalizable CSI acquisition. The proposed framework employs a predictive foundation model trained on large-scale cross-domain CSI data to extract universal channel representations and provide predictive priors with strong cross-scenario transferability. A pilot processing network based on a vision transformer architecture is further designed to capture spatial, temporal, and frequency correlations from pilot observations. An efficient fusion mechanism integrates predictive priors with real-time measurements, enabling reliable CSI reconstruction even under sparse or noisy conditions. Extensive evaluations across diverse configurations demonstrate that the proposed estimator significantly outperforms both classical and data-driven baselines in accuracy, robustness, and generalization capability.

cs.IT↗

arXiv2026

Improving Channel Estimation via Multimodal Diffusion Models with Flow Matching

Deep generative models offer a powerful alternative to conventional channel estimation by learning complex channel distributions. By integrating the rich environmental information available in modern sensing-aided networks, this paper proposes MultiCE-Flow, a multimodal channel estimation framework based on flow matching and diffusion transformer (DiT). We design a specialized multimodal perception module that fuses LiDAR, camera, and location data into a semantic condition, while treating sparse pilots as a structural condition. These conditions guide a DiT backbone to reconstruct high-fidelity channels. Unlike standard diffusion models, we employ flow matching to learn a linear trajectory from noise to data, enabling efficient one-step sampling. By leveraging environmental semantics, our method mitigates the ill-posed nature of estimation with sparse pilots. Extensive experiments demonstrate that MultiCE-Flow consistently outperforms traditional baselines and existing generative models. Notably, it exhibits superior robustness to out-of-distribution scenarios and varying pilot densities, making it suitable for environment-aware communication systems.

cs.LG↗

arXiv2026

Generative Diffusion Models for High Dimensional Channel Estimation

Along with the prosperity of generative artificial intelligence (AI), its potential for solving conventional challenges in wireless communications has also surfaced. Inspired by this trend, we investigate the application of the advanced diffusion models (DMs), a representative class of generative AI models, to high dimensional wireless channel estimation. By capturing the structure of multiple-input multiple-output (MIMO) wireless channels via a deep generative prior encoded by DMs, we develop a novel posterior inference method for channel reconstruction. We further adapt the proposed method to recover channel information from low-resolution quantized measurements. Additionally, to enhance the over-the-air viability, we integrate the DM with the unsupervised Stein's unbiased risk estimator to enable learning from noisy observations and circumvent the requirements for ground truth channel data that is hardly available in practice. Results reveal that the proposed estimator achieves high-fidelity channel recovery while reducing estimation latency by a factor of 10 compared to state-of-the-art schemes, facilitating real-time implementation. Moreover, our method outperforms existing estimators while reducing the pilot overhead by half, showcasing its scalability to ultra-massive antenna arrays.

cs.IT↗

arXiv2026

Hierarchical Industrial Demand Forecasting with Temporal and Uncertainty Explanations

Hierarchical time-series forecasting is essential for demand prediction across various industries. While machine learning models have obtained significant accuracy and scalability on such forecasting tasks, the interpretability of their predictions, informed by application, is still largely unexplored. To bridge this gap, we introduce a novel interpretability method for large hierarchical probabilistic time-series forecasting, adapting generic interpretability techniques while addressing challenges associated with hierarchical structures and uncertainty. Our approach offers valuable interpretative insights in response to real-world industrial supply chain scenarios, including 1) the significance of various time-series within the hierarchy and external variables at specific time points, 2) the impact of different variables on forecast uncertainty, and 3) explanations for forecast changes in response to modifications in the training dataset. To evaluate the explainability method, we generate semi-synthetic datasets based on real-world scenarios of explaining hierarchical demands for over ten thousand products at a large chemical company. The experiments showed that our explainability method successfully explained state-of-the-art industrial forecasting methods with significantly higher explainability accuracy. Furthermore, we provide multiple real-world case studies that show the efficacy of our approach in identifying important patterns and explanations that help stakeholders better understand the forecasts. Additionally, our method facilitates the identification of key drivers behind forecasted demand, enabling more informed decision-making and strategic planning. Our approach helps build trust and confidence among users, ultimately leading to better adoption and utilization of hierarchical forecasting models in practice.

cs.LG↗

arXiv2026

ATD: Improved Transformer with Adaptive Token Dictionary for Image Restoration

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a long-standing problem for transformer-based architectures. Due to the quadratic complexity of self-attention, existing methods often restrict attention to local windows, resulting in limited receptive field and suboptimal performance. To address this issue, we propose Adaptive Token Dictionary (ATD), a novel transformer-based architecture for image restoration that enables global dependency modeling with linear complexity relative to image size. The ATD model incorporates a learnable token dictionary, which summarizes external image priors (i.e., typical image structures) during the training process. To utilize this information, we introduce a token dictionary cross-attention (TDCA) mechanism that enhances the input features via interaction with the learned dictionary. Furthermore, we exploit the category information embedded in the TDCA attention maps to group input features into multiple categories, each representing a cluster of similar features across the image and serving as an attention group. We also integrate the learned category information into the feed-forward network to further improve feature fusion. ATD and its lightweight version ATD-light, achieve state-of-the-art performance on multiple image super-resolution benchmarks. Moreover, we develop ATD-U, a multi-scale variant of ATD, to address other image restoration tasks, including image denoising and JPEG compression artifacts removal. Extensive experiments demonstrate the superiority of out proposed models, both quantitatively and qualitatively.

cs.CV↗

arXiv2026

VR Calm Plus: Coupling a Squeezable Tangible Interaction with Immersive VR for Stress Regulation

While Virtual Reality (VR) is increasingly employed for stress management, most applications rely heavily on audio-visual stimuli and overlook the therapeutic potential of squeezing engagement. To address this gap, we introduce VR Calm Plus, a multimodal system that integrates a pressure-sensitive plush toy into an interactive VR environment. This interface allows users to dynamically modulate the virtual atmosphere through physical squeezing actions, fostering a deeper sense of embodied relaxation. We evaluated the system with 40 participants using PANAS-X surveys, subjective questionnaires, physiological measures (heart rate, skin conductance, pulse rate variability), and semi-structured interviews. Results demonstrate that, compared to a visual-only baseline, squeeze-based interaction significantly enhances positive affect and perceived relaxation. Physiological data further revealed a state of "active relaxation", characterized by greater reductions in heart rate and preserved autonomic flexibility (PRV), alongside sustained emotional engagement (GSR). Our findings highlight the value of coupling tangible input with immersive environments to support emotional well-being and offer design insights for future VR-based mental health tools.

cs.HC↗

arXiv2025

Super-Resolution ISAC Receivers: An MCMC-Based Gridless Sparse Bayesian Learning Approach

Integrated sensing and communication (ISAC) is crucial for low-altitude wireless networks (LAWNs), where the safety-critical demand for high-accuracy sensing creates a trade-off between precision and complexity for conventional methods. To address this, we propose a novel gridless sparse Bayesian learning (SBL) framework for joint super-resolution multi-target detection and high-accuracy parameter estimation with manageable computational cost. Our model treats target parameters as continuous variables to bypass the grid limitations of conventional approaches. This SBL formulation, however, transforms the estimation task into a challenging high-dimensional inference problem, which we address by developing an enhanced gradient-based Markov chain Monte Carlo algorithm. Our method integrates mini-batch sampling and the Adam optimizer to ensure computational efficiency and rapid convergence. Finally, we validate the framework's robustness in strong clutter and provide a theoretical benchmark by deriving the corresponding Bayesian Cramer-Rao bound. Simulation results demonstrate remarkable super-resolution capabilities, successfully resolving multiple targets separated by merely 50% of the Rayleigh limit in range, 17% in velocity, and 52% in angle. At a signal-to-noise ratio of 20 dB, the algorithm achieves a multi-target detection probability exceeding 90% while concurrently delivering ultra-high accuracy, with root mean square error of 0.07 m, 0.024 m/s, and 0.015 degree for range, velocity, and angle, respectively. This robust performance, demonstrated against strong clutter, showcases its suitability for practical ISAC-LAWNs applications.

eess.SP↗

arXiv2025

Consistency Trajectory Matching for One-Step Generative Super-Resolution

Current diffusion-based super-resolution (SR) approaches achieve commendable performance at the cost of high inference overhead. Therefore, distillation techniques are utilized to accelerate the multi-step teacher model into one-step student model. Nevertheless, these methods significantly raise training costs and constrain the performance of the student model by the teacher model. To overcome these tough challenges, we propose Consistency Trajectory Matching for Super-Resolution (CTMSR), a distillation-free strategy that is able to generate photo-realistic SR results in one step. Concretely, we first formulate a Probability Flow Ordinary Differential Equation (PF-ODE) trajectory to establish a deterministic mapping from low-resolution (LR) images with noise to high-resolution (HR) images. Then we apply the Consistency Training (CT) strategy to directly learn the mapping in one step, eliminating the necessity of pre-trained diffusion model. To further enhance the performance and better leverage the ground-truth during the training process, we aim to align the distribution of SR results more closely with that of the natural images. To this end, we propose to minimize the discrepancy between their respective PF-ODE trajectories from the LR image distribution by our meticulously designed Distribution Trajectory Matching (DTM) loss, resulting in improved realism of our recovered HR images. Comprehensive experimental results demonstrate that the proposed methods can attain comparable or even superior capabilities on both synthetic and real datasets while maintaining minimal inference latency.

cs.CV↗

arXiv2025

Conditional Diffusion Model-Enabled Scenario-Specific Neural Receivers for Superimposed Pilot Schemes

Neural receivers have demonstrated strong performance in wireless communication systems. However, their effectiveness typically depends on access to large-scale, scenario-specific channel data for training, which is often difficult to obtain in practice. Recently, generative artificial intelligence (AI) models, particularly diffusion models (DMs), have emerged as effective tools for synthesizing high-dimensional data. This paper presents a scenario-specific channel generation method based on conditional DMs, which accurately model channel distributions conditioned on user location and velocity information. The generated synthetic channel data are then employed for data augmentation to improve the training of a neural receiver designed for superimposed pilot-based transmission. Experimental results show that the proposed method generates high-fidelity channel samples and significantly enhances neural receiver performance in the target scenarios, outperforming conventional data augmentation and generative adversarial network-based techniques.

cs.IT↗

arXiv2025

Robust MIMO Channel Estimation Using Energy-Based Generative Diffusion Models

Channel estimation for massive multiple-input multiple-output (MIMO) systems is fundamentally constrained by excessive pilot overhead and high estimation latency. To overcome these obstacles, recent studies have leveraged deep generative networks to capture the prior distribution of wireless channels. In this paper, we propose a novel estimation framework that integrates an energy-based generative diffusion model (DM) with the Metropolis-Hastings (MH) principle. By reparameterizing the diffusion process with an incorporated energy function, the framework explicitly estimates the unnormalized log-prior, while MH corrections refine the sampling trajectory, mitigate deviations, and enhance robustness, ultimately enabling accurate posterior sampling for high-fidelity channel estimation. Numerical results reveal that the proposed approach significantly improves estimation accuracy compared with conventional parameterized DMs and other baseline methods, particularly in cases with limited pilot overhead.

cs.IT↗

arXiv2025

Low-Complexity MIMO Channel Estimation with Latent Diffusion Models

Deep generative models offer a powerful alternative to conventional channel estimation by learning the complex prior distribution of wireless channels. Capitalizing on this potential, this paper proposes a novel channel estimation algorithm based on latent diffusion models (LDMs), termed posterior sampling with latent diffusion for channel estimation (PSLD-CE). The core of our approach is a lightweight LDM architecture specifically designed for channel estimation, which serves as a powerful generative prior to capture the intricate channel distribution. Furthermore, we enhance the diffusion posterior sampling process by introducing an effective approximation for the likelihood term and a tailored self-consistency constraint on the variational autoencoder latent space. Extensive experimental results demonstrate that PSLD-CE consistently outperforms a wide range of existing methods. Notably, these significant performance gains are achieved while maintaining low computational complexity and fast inference speed, establishing our method as a highly promising and practical solution for next-generation wireless systems.

cs.IT↗

arXiv2025

Next-Generation AI-Native Wireless Communications: MCMC-Based Receiver Architectures for Unified Processing

The multiple-input multiple-output (MIMO) receiver processing is a key technology for current and next-generation wireless communications. However, it faces significant challenges related to complexity and scalability as the number of antennas increases. Artificial intelligence (AI), a cornerstone of next-generation wireless networks, offers considerable potential for addressing these challenges. This paper proposes an AI-driven, universal MIMO receiver architecture based on Markov chain Monte Carlo (MCMC) techniques. Unlike existing AI-based methods that treat receiver processing as a black box, our MCMC-based approach functions as a generic Bayesian computing engine applicable to various processing tasks, including channel estimation, symbol detection, and channel decoding. This method enhances the interpretability, scalability, and flexibility of receivers in diverse scenarios. Furthermore, the proposed approach integrates these tasks into a unified probabilistic framework, thereby enabling overall performance optimization. This unified framework can also be seamlessly combined with data-driven learning methods to facilitate the development of fully intelligent communication receivers.

cs.IT↗

arXiv2025

Identifying Fixed Points in the Three-Body Problem Using a High-Order Transfer Map

Periodic orbits (POs) play a central role in the circular restricted three-body problem (CRTBP). This paper introduces a method to search for POs by identifying single- and multiple-revolution fixed points in chosen Poincare maps that describe the CRTBP dynamics, with a theoretical capability to detect all fixed points across arbitrary revolution counts exhaustively.First, high-order transfer maps (HOTMs), represented as polynomials, are constructed within the differential algebra (DA) framework for both planar and spatial CRTBP to map states between successive Poincare section crossings, with the Jacobi constant used to reduce the number of independent variables. Next, an automatic domain splitting (ADS) strategy is employed to generate subdomains, preserving HOTM accuracy, with an integrated feasibility estimation to reduce ADS's computation burden.Then, a two-stage HOTM-based polynomial optimization framework is introduced, first identifying combinable subdomain sequences and then refining the fixed point solutions. Finally, the method is applied to the Earth-Moon CRTBP, identifying POs up to nine revolutions in the planar case and four in the spatial case. Known families such as distant retrograde orbits (DROs) and Lyapunov orbits are recovered, along with a previously undocumented family that exhibits a hybrid character between DROs and Lyapunov orbits.

astro-ph.EP↗