arXiv subjects

Xiaoyu Zhang

Publications and source records attributed to Xiaoyu Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2026

SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras

High-quality 4D reconstruction enables photorealistic and immersive rendering of the dynamic real world. However, unlike static scenes that can be fully captured with a single camera, high-quality dynamic scenes typically require dense arrays of tens or even hundreds of synchronized cameras. Dependence on such costly lab setups severely limits practical scalability. To this end, we propose a sparse-camera dynamic reconstruction framework that exploits abundant yet inconsistent generative observations. Our key innovation is the Spatio-Temporal Distortion Field, which provides a unified mechanism for modeling inconsistencies in generative observations across both spatial and temporal dimensions. Building on this, we develop a complete pipeline that enables 4D reconstruction from sparse and uncalibrated camera inputs. We evaluate our method on multi-camera dynamic scene benchmarks, achieving spatio-temporally consistent high-fidelity renderings and significantly outperforming existing approaches. Project page available at https://inspatio.github.io/sparse-cam4d/

cs.CV↗

arXiv2026

Ensemble-Based Uncertainty Estimation for Code Correctness Estimation

Large language models (LLMs) have demonstrated remarkable capabilities in generating programs from natural language descriptions, yet ensuring their correctness without an external oracle remains a critical challenge. To solve the challenge, existing methods often rely on uncertainty estimation, measuring the consistency of semantics or execution behaviors across multiple samples generated by a single model. However, we observe that a single model can often converge to a consistent but incorrect solution, rendering such consistency-based proxies ineffective. To address this, we propose Ensemble Semantic Entropy (ESE), which estimates uncertainty by evaluating the consistency of samples aggregated across an ensemble of models. Experiments on LiveCodeBench demonstrate that ESE correlates more strongly with program correctness than single-model semantic entropy. Notably, in selective generation tasks with strict false-positive rate constraints, ESE improves prediction accuracy by 53.4%. Furthermore, by leveraging ESE as the decision signal, we propose a cascading test-time scaling framework Cas, which maintains performance while reducing FLOPs by 64.9% compared to single-model scaling, offering a new perspective on balancing parameter and inference scaling.

cs.SE↗

arXiv2026

PRCCF: A Persona-guided Retrieval and Causal-aware Cognitive Filtering Framework for Emotional Support Conversation

Emotional Support Conversation (ESC) aims to alleviate individual emotional distress by generating empathetic responses. However, existing methods face challenges in effectively supporting deep contextual understanding. To address this issue, we propose PRCCF, a Persona-guided Retrieval and Causality-aware Cognitive Filtering framework. Specifically, the framework incorporates a persona-guided retrieval mechanism that jointly models semantic compatibility and persona alignment to enhance response generation. Furthermore, it employs a causality-aware cognitive filtering module to prioritize causally relevant external knowledge, thereby improving contextual cognitive understanding for emotional reasoning. Extensive experiments on the ESConv dataset demonstrate that PRCCF outperforms state-of-the-art baselines on both automatic metrics and human evaluations. Our code is publicly available at: https://github.com/YancyLyx/PRCCF.

cs.CL↗

arXiv2026

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements

Large language models (LLMs) are increasingly deployed under diverse numerical precision configurations, including standard floating-point formats (e.g., bfloat16 and float16) and quantized integer formats (e.g., int16 and int8), to meet efficiency and resource constraints. However, minor inconsistencies between LLMs of different precisions are difficult to detect and are often overlooked by existing evaluation methods. In this paper, we present PrecisionDiff, an automated differential testing framework for systematically detecting precision-induced behavioral disagreements in LLMs. PrecisionDiff generates precision-sensitive test inputs and performs cross-precision comparative analysis to uncover subtle divergences that remain hidden under conventional testing strategies. To demonstrate its practical significance, we instantiate PrecisionDiff on the alignment verification task, where precision-induced disagreements manifest as jailbreak divergence-inputs that are rejected under one precision may produce harmful responses under another. Experimental results show that such behavioral disagreements are widespread across multiple open-source aligned LLMs and precision settings, and that PrecisionDiff significantly outperforms vanilla testing methods in detecting these issues. Our work enables automated precision-sensitive test generation, facilitating effective pre-deployment evaluation and improving precision robustness during training.

cs.AI↗

arXiv2026

Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents

Code large language models (CodeLLMs) and agents are increasingly being integrated into complex software engineering tasks spanning the entire Software Development Life Cycle (SDLC). Benchmarking is critical for rigorously evaluating these capabilities. However, despite their growing significance, there remains a lack of comprehensive reviews that examine these benchmarks from an SDLC perspective. To bridge this gap, we propose a tiered analysis framework to systematically review 178 benchmarks from 461 papers, comprehensively characterizing them from the perspective of the SDLC. Our findings reveal a notable imbalance in the coverage of current benchmarks, with approximately 61\% focused on the software implementation phase in SDLC, while requirements engineering and software design phases receive minimal attention at only 5\% and 3\%, respectively. % Additionally, anti-contamination strategies are largely absent from current benchmarks, leading to an increased risk of data leakage. Furthermore, current benchmarks lack effective anti-contamination strategies, posing significant risks of data leakage and potentially inflated performance assessments. Finally, we identify key open challenges in current research and outline future directions to narrow the gap between the theoretical capabilities of CodeLLMs and agents and their practical effectiveness in real-world scenarios.

cs.SE↗

arXiv2026

PersonaMail: Learning and Adapting Personal Communication Preferences for Context-Aware Email Writing

LLM-assisted writing has seen rapid adoption in interpersonal communication, yet current systems often fail to capture the subtle tones essential for effectiveness. Email writing exemplifies this challenge: effective messages require careful alignment with intent, relationship, and context beyond mere fluency. Through formative studies, we identified three key challenges: articulating nuanced communicative intent, making modifications at multiple levels of granularity, and reusing effective tone strategies across messages. We developed PersonaMail, a system that addresses these gaps through structured communication factor exploration, granular editing controls, and adaptive reuse of successful strategies. Our evaluation compared PersonaMail against standard LLM interfaces, and showed improved efficiency in both immediate and repeated use, alongside higher user satisfaction. We contribute design implications for AI-assisted communication systems that prioritize interpersonal nuance over generic text generation.

cs.HC↗

arXiv2026

Strengthenings of Mazur's Conjecture for Higher Heegner Points

We establish quantitative strengthenings of Mazur's conjecture regarding the non-torsion property of higher Heegner points on modular and Shimura curves, confirming both a vertical version for sufficiently large powers $n$ and a horizontal version for primes $p \gg 1$. Distinct from previous strategies by Cornut and Vatsal that relied on Ratner's theorems on unipotent flows and required restrictive hypotheses on level structures, our approach circumvents these constraints by exploiting the interplay between Galois orbits and Hecke orbits. By quantifying the relative size of these orbits, we reduce the problem to ergodic results concerning the equidistribution of Hecke operators and the classification of joining measures. This method allows for the analysis of simultaneous supersingular reductions without requiring the surjectivity of reduction maps.

math.NT↗

arXiv2026

Understanding Internal Representations of Recommendation Models with Sparse Autoencoders

Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the inherent complexity and opacity of deep learning models pose challenges for model-level interpretation. Moreover, most existing methods for interpreting recommendation models are tailored to specific architectures or model types, limiting their generalizability across different types of recommenders. In this paper, we propose RecSAE, a generalizable probing framework that interprets Recommendation models with Sparse AutoEncoders. The framework extracts interpretable latents from the internal representations of recommendation models, and links them to semantic concepts for interpretations. It does not alter original models during interpretations and also enables targeted tuning to models. Experiments on three types of recommendation models (general, graph-based, sequential) with four widely used public datasets demonstrate the effectiveness and generalization of RecSAE framework. The interpreted concepts are further validated by human experts, showing strong alignment with human perception. Overall, RecSAE serves as a novel step in both model-level interpretations to various types of recommendation models without affecting their functions and offering potential for targeted tuning of models.

cs.IR↗

arXiv2026

A Hybrid Framework Combining Autoregression and Common Factors for Matrix Time Series

Matrix-valued time series are ubiquitous in modern economics and finance, yet modeling them requires navigating a trade-off between flexibility and parsimony. We propose the Matrix Autoregressive model with Common Factors (MARCF), a unified framework for high-dimensional matrix time series that bridges the structural gap between the Matrix Autoregression (MAR) and Matrix Factor Model (MFM). While MAR typically assumes distinct predictor and response subspaces and MFM enforces identical ones, MARCF explicitly characterizes the intersection of these subspaces. By decomposing the coefficient matrices into common, predictor-specific, and response-specific components, the framework accommodates distinct input and output structures while exploiting their overlap for dimension reduction. We develop a regularized gradient descent estimator that is scalable for high-dimensional data and can efficiently handle the non-convex parameter space. Theoretical analysis establishes local linear convergence of the algorithm and statistical consistency of the estimator under high-dimensional scaling. The estimation efficiency and interpretability of the proposed methods are demonstrated through simulations and an application to global macroeconomic forecasting.

stat.ME↗

arXiv2026

PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems

With the increasing deployment of large language models (LLMs) in affective agents and AI systems, maintaining a consistent and authentic LLM personality becomes critical for user trust and engagement. However, existing work overlooks a fundamental psychological consensus that personality traits are dynamic and context-dependent. To bridge this gap, we introduce PTCBENCH, a systematic benchmark designed to quantify the consistency of LLM personalities under controlled situational contexts. PTCBENCH subjects models to 12 distinct external conditions spanning diverse location contexts and life events, and rigorously assesses the personality using the NEO Five-Factor Inventory. Our study on 39,240 personality trait records reveals that certain external scenarios (e.g., "Unemployment") can trigger significant personality changes of LLMs, and even alter their reasoning capabilities. Overall, PTCBENCH establishes an extensible framework for evaluating personality consistency in realistic, evolving environments, offering actionable insights for developing robust and psychologically aligned AI systems.

cs.CL↗

arXiv2025

Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?

Stage lighting is a vital component in live music performances, shaping an engaging experience for both musicians and audiences. In recent years, Automatic Stage Lighting Control (ASLC) has attracted growing interest due to the high costs of hiring or training professional lighting engineers. However, most existing ASLC solutions only classify music into limited categories and map them to predefined light patterns, resulting in formulaic and monotonous outcomes that lack rationality. To address this gap, this paper presents Skip-BART, an end-to-end model that directly learns from experienced lighting engineers and predict vivid, human-like stage lighting. To the best of our knowledge, this is the first work to conceptualize ASLC as a generative task rather than merely a classification problem. Our method adapts the BART model to take audio music as input and produce light hue and value (intensity) as output, incorporating a novel skip connection mechanism to enhance the relationship between music and light within the frame grid. To address the lack of available datasets, we create the first stage lighting dataset, along with several pre-training and transfer learning techniques to improve model training with limited data. We validate our method through both quantitative analysis and an human evaluation, demonstrating that Skip-BART outperforms conventional rule-based methods across all evaluation metrics and shows only a limited gap compared to real lighting engineers. To support further research, we have made our self-collected dataset, code, and trained model parameters available at https://github.com/RS2002/Skip-BART .

cs.LG↗

arXiv2025

Compute-in-Memory Implementation of State Space Models for Event Sequence Processing

State space models (SSMs) have recently emerged as a powerful framework for long sequence processing, outperforming traditional methods on diverse benchmarks. Fundamentally, SSMs can generalize both recurrent and convolutional networks and have been shown to even capture key functions of biological systems. Here we report an approach to implement SSMs in energy-efficient compute-in-memory (CIM) hardware to achieve real-time, event-driven processing. Our work re-parameterizes the model to function with real-valued coefficients and shared decay constants, reducing the complexity of model mapping onto practical hardware systems. By leveraging device dynamics and diagonalized state transition parameters, the state evolution can be natively implemented in crossbar-based CIM systems combined with memristors exhibiting short-term memory effects. Through this algorithm and hardware co-design, we show the proposed system offers both high accuracy and high energy efficiency while supporting fully asynchronous processing for event-based vision and audio tasks.

eess.SP↗

arXiv2025

Scale-Invariant Robust Estimation of High-Dimensional Kronecker-Structured Matrices

High-dimensional Kronecker-structured estimation faces a conflict between non-convex scaling ambiguities and statistical robustness. The arbitrary factor scaling distorts gradient magnitudes, rendering standard fixed-threshold robust methods ineffective. We resolve this via Scaled Robust Gradient Descent (SRGD), which stabilizes optimization by de-scaling gradients before truncation. To further enforce interpretability, we introduce Scaled Hard Thresholding (SHT) for invariant variable selection. A two-step estimation procedure, built upon robust initialization and SRGD--SHT iterative updates, is proposed for canonical matrix problems, such as trace regression, matrix GLMs, and bilinear models. The convergence rates are established for heavy-tailed predictors and noise, identifying a phase transition where optimal convergence rates recover under finite noise variance and degrade optimally for heavier tails. Experiments on simulated data and two real-world applications confirm superior robustness and efficiency of the proposed procedure.

stat.ME↗

arXiv2025

Hypervelocity Impact Debris Cloud Trajectory-Planning based on Additive Manufactured Lattice Structures

Space debris and micrometeoroid (MMOD) impacts pose a serious threat to the safe operation of spacecraft. However, traditional protective structures typically suffer from limitations such as excessive thickness and inadequate load-bearing capacity. Guided by the design concepts of debris-cloud deflection and hierarchical energy dissipation, this study proposes a trajectory-planning lattice protective structure. First, the lattice parameters and geometry were designed according to the functional relationship between the incident angle and the transmitted/ricochet trajectory angles. Subsequently, multi-angle hypervelocity impact experiments were carried out to evaluate the proposed lattice protection structure. In combination with post-impact CT three-dimensional reconstruction and smoothed particle hydrodynamics (SPH) numerical simulations, the protective mechanisms of the lattice structure were systematically characterized and clarified. The results demonstrate that, for three oblique incidence conditions, the lattice structure remained intact and significantly deflected the debris-cloud momentum direction while effectively dissipating its kinetic energy. The angled plates with gradient designs enabled continuous changes in the momentum direction and stepwise kinetic energy dissipation through multiple cycles of debrisation, dispersion, and trajectory deflection. This research presents a novel, engineering-ready approach for spacecraft MMOD protection and validates the potential of trajectory-planning lattice structures for hypervelocity impact defense.

physics.app-ph↗

arXiv2025

GeoTexDensifier: Geometry-Texture-Aware Densification for High-Quality Photorealistic 3D Gaussian Splatting

3D Gaussian Splatting (3DGS) has recently attracted wide attentions in various areas such as 3D navigation, Virtual Reality (VR) and 3D simulation, due to its photorealistic and efficient rendering performance. High-quality reconstrution of 3DGS relies on sufficient splats and a reasonable distribution of these splats to fit real geometric surface and texture details, which turns out to be a challenging problem. We present GeoTexDensifier, a novel geometry-texture-aware densification strategy to reconstruct high-quality Gaussian splats which better comply with the geometric structure and texture richness of the scene. Specifically, our GeoTexDensifier framework carries out an auxiliary texture-aware densification method to produce a denser distribution of splats in fully textured areas, while keeping sparsity in low-texture regions to maintain the quality of Gaussian point cloud. Meanwhile, a geometry-aware splitting strategy takes depth and normal priors to guide the splitting sampling and filter out the noisy splats whose initial positions are far from the actual geometric surfaces they aim to fit, under a Validation of Depth Ratio Change checking. With the help of relative monocular depth prior, such geometry-aware validation can effectively reduce the influence of scattered Gaussians to the final rendering quality, especially in regions with weak textures or without sufficient training views. The texture-aware densification and geometry-aware splitting strategies are fully combined to obtain a set of high-quality Gaussian splats. We experiment our GeoTexDensifier framework on various datasets and compare our Novel View Synthesis results to other state-of-the-art 3DGS approaches, with detailed quantitative and qualitative evaluations to demonstrate the effectiveness of our method in producing more photorealistic 3DGS models.

cs.CV↗

arXiv2025

CogMCTS: A Novel Cognitive-Guided Monte Carlo Tree Search Framework for Iterative Heuristic Evolution with Large Language Models

Automatic Heuristic Design (AHD) is an effective framework for solving complex optimization problems. The development of large language models (LLMs) enables the automated generation of heuristics. Existing LLM-based evolutionary methods rely on population strategies and are prone to local optima. Integrating LLMs with Monte Carlo Tree Search (MCTS) improves the trade-off between exploration and exploitation, but multi-round cognitive integration remains limited and search diversity is constrained. To overcome these limitations, this paper proposes a novel cognitive-guided MCTS framework (CogMCTS). CogMCTS tightly integrates the cognitive guidance mechanism of LLMs with MCTS to achieve efficient automated heuristic optimization. The framework employs multi-round cognitive feedback to incorporate historical experience, node information, and negative outcomes, dynamically improving heuristic generation. Dual-track node expansion combined with elite heuristic management balances the exploration of diverse heuristics and the exploitation of high-quality experience. In addition, strategic mutation modifies the heuristic forms and parameters to further enhance the diversity of the solution and the overall optimization performance. The experimental results indicate that CogMCTS outperforms existing LLM-based AHD methods in stability, efficiency, and solution quality.

cs.AI↗

arXiv2025

Efficient Beamforming Optimization for STAR-RIS-Assisted Communications: A Gradient-Based Meta Learning Approach

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) has emerged as a promising technology to realize full-space coverage and boost spectral efficiency in next-generation wireless networks. Yet, the joint design of the base station precoding matrix as well as the STAR-RIS transmission and reflection coefficient matrices leads to a high-dimensional, strongly nonconvex, and NP-hard optimization problem. Conventional alternating optimization (AO) schemes typically involve repeated large-scale matrix inversion operations, resulting in high computational complexity and poor scalability, while existing deep learning approaches often rely on expensive pre-training and large network models. In this paper, we develop a gradient-based meta learning (GML) framework that directly feeds optimization gradients into lightweight neural networks, thereby removing the need for pre-training and enabling fast adaptation. Specifically, we design dedicated GML-based schemes for both independent-phase and coupled-phase STAR-RIS models, effectively handling their respective amplitude and phase constraints while achieving weighted sum-rate performance very close to that of AO-based benchmarks. Extensive simulations demonstrate that, for both phase models, the proposed methods substantially reduce computational overhead, with complexity growing nearly linearly when the number of BS antennas and STAR-RIS elements grows, and yielding up to 10 times runtime speedup over AO, which confirms the scalability and practicality of the proposed GML method for large-scale STAR-RIS-assisted communications.

eess.SP↗

arXiv2025

YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidance

Singing Voice Synthesis (SVS) remains constrained in practical deployment due to its strong dependence on accurate phoneme-level alignment and manually annotated melody contours, requirements that are resource-intensive and hinder scalability. To overcome these limitations, we propose a melody-driven SVS framework capable of synthesizing arbitrary lyrics following any reference melody, without relying on phoneme-level alignment. Our method builds on a Diffusion Transformer (DiT) architecture, enhanced with a dedicated melody extraction module that derives melody representations directly from reference audio. To ensure robust melody encoding, we employ a teacher model to guide the optimization of the melody extractor, alongside an implicit alignment mechanism that enforces similarity distribution constraints for improved melodic stability and coherence. Additionally, we refine duration modeling using weakly annotated song data and introduce a Flow-GRPO reinforcement learning strategy with a multi-objective reward function to jointly enhance pronunciation clarity and melodic fidelity. Experiments show that our model achieves superior performance over existing approaches in both objective measures and subjective listening tests, especially in zero-shot and lyric adaptation settings, while maintaining high audio quality without manual annotation. This work offers a practical and scalable solution for advancing data-efficient singing voice synthesis. To support reproducibility, we release our inference code and model checkpoints.

cs.SD↗