Searcharxiv⌕ Search

arXiv subjects

Qi Zhou

Publications and source records attributed to Qi Zhou.

At least 55 records · Page 3Linked to original sources
arXiv2026

UModel: An Agent-Ready Observability Data Modeling Method at Scale

When networked system failures occur, automatically performing Root Cause Analysis (RCA) using observability data is critical for ensuring networked system reliability. Recently, LLM-based agents have shown promise for automating this diagnosis process through advanced reasoning and autonomous exploration. However, existing observability frameworks remain archaic, characterized by fragmented data silos, incompatible schemas, and insufficient semantic metadata, preventing agents from establishing the complex relationships required for effective RCA. To address these challenges, we present UModel, a unified ontological framework that shifts observability from data-centric to object-centric modeling. UModel constructs a virtual ontological layer where heterogeneous telemetry, entities, and expert knowledge are standardized as objects and interconnected via semantic graphs. In addition, we introduce U-SPL, a pipeline-based query interface that enables agents to autonomously explore system topologies and correlate multimodal data. By re-modeling the "AIOps 2025 Challenge" dataset using UModel, the precision of root cause localization improved by 8%, demonstrating that enhanced data organization can significantly increase the accuracy of downstream tasks. UModel provides a scalable modeling framework that, in its deployment at Alibaba Cloud for more than one year, has served tens of thousands of users, sustained millions of operations per second, and delivered sub-second query latency.

cs.SE↗
arXiv2026

ERNIE-Image Technical Report

We introduce ERNIE-Image, an open-source text-to-image generation model built upon an 8B single-stream DiT architecture. ERNIE-Image aims to bridge the gap between current open-source models and leading closed-source systems through more effective mining of large-scale pre-training data and improved supervision quality throughout training. During pre-training, we adopt a bottom-up data construction pipeline that combines fine-grained image categorization, rich caption annotation, aesthetic assessment, and hierarchical sampling. This strategy reduces data noise while preserving long-tail concepts and detailed real-world knowledge, providing a stronger foundation for complex generation tasks. In the post-training stage, we use a top-down data construction pipeline for high-demand scenarios, diversify prompt annotations to better match real user inputs, and apply a stabilized DPO strategy to align the model with human aesthetic preferences. We further train ERNIE-Image-Turbo for efficient 8-NFE generation and propose MT-DMD to mitigate capability drift during distillation. To make the model easier to use in practical scenarios, we equip it with a lightweight Prompt Enhancer that expands concise user intents into structured visual descriptions. In addition, we develop ERNIE-Image-Aes, an industrial-grade aesthetic model, together with ERNIE-Image-Aes-1K, a human-annotated benchmark for realistic aesthetic evaluation. Extensive qualitative and quantitative experiments show that ERNIE-Image achieves leading performance among open-source models and approaches top-tier commercial models in instruction following, text rendering, and aesthetic quality. We release the trained models and aesthetic resources to facilitate further academic research and technical progress in the AIGC community.

cs.CV↗
arXiv2026

SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling

Industrial recommender systems increasingly leverage lifelong user behavior histories and rich multi-modal content to capture evolving user preferences. However, effectively integrating multi-modal features into lifelong interest modeling remains challenging due to the inherent misalignment between multi-modal and collaborative spaces. Existing paradigms typically rely on separate modeling of multi-modal sequence and behavior sequence, and late fusion to alleviate the modality gap, which results in coarse-grained multi-modal representation and limited integration. In this paper, we propose SIREN, a unified multi-granularity semantic interaction framework for multi-modal lifelong user interest modeling. In the General Search Unit stage, we introduce two alternative retrieval strategies: multi-modal similarity-based soft retrieval for retrieval effectiveness, and Semantic ID (SemID)-based hard retrieval for efficient industrial serving. For the Exact Search Unit stage, we explicitly incorporate target-aware relevance via coarse similarity buckets and fine-grained prefix-encoded SemIDs, enabling unified interaction with collaborative ID features within the target-conditioned transformer architecture. Extensive experiments on the offline dataset demonstrate that SIREN achieves a state-of-the-art GAUC. Online A/B tests further demonstrate consistent GMV gains across multiple production scenarios, including +2.28% in Weixin Moments, +3.87% in Weixin Official Accounts, and +1.61% in Weixin Channels. From July 2025, SIREN has been fully launched for full-traffic serving in Tencent's advertising platform.

cs.IR↗
arXiv2026

InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion

Recent advances in large language models (LLMs) have intensified efforts to fuse heterogeneous open-source models into a unified system that inherits their complementary strengths. Existing logit-based fusion methods maintain inference efficiency but treat vocabulary dimensions independently, overlooking semantic dependencies encoded by cross-dimension interactions. These dependencies reflect how token types interact under a model's internal reasoning and are essential for aligning models with diverse generation behaviors. To explicitly model these dependencies, we propose \textbf{InfiGFusion}, the first structure-aware fusion framework with a novel \textit{Graph-on-Logits Distillation} (GLD) loss. Specifically, we retain the top-$k$ logits per output and aggregate their outer products across sequence positions to form a global co-activation graph, where nodes represent vocabulary channels and edges quantify their joint activations. To ensure scalability and efficiency, we design a sorting-based closed-form approximation that reduces the original $O(n^4)$ cost of Gromov-Wasserstein distance to $O(n \log n)$, with provable approximation guarantees. Experiments across multiple fusion settings show that GLD consistently improves fusion quality and stability. InfiGFusion outperforms SOTA models and fusion baselines across 11 benchmarks spanning reasoning, coding, and mathematics. It shows particular strength in complex reasoning tasks, with +35.6 improvement on Multistep Arithmetic and +37.06 on Causal Judgement over SFT, demonstrating superior multi-step and relational inference.

cs.CL↗
arXiv2026

Model Merging Scaling Laws in Large Language Models

We study empirical scaling laws for language model merging measured by cross-entropy. Despite its wide practical use, merging lacks a quantitative rule that predicts returns as we add experts or scale the model size. We identify a compact power law that links model size and expert number: the size-dependent floor decreases with model capacity, while the merging tail exhibits clear diminishing returns in the number of experts. The law holds in-domain and cross-domain, tightly fits measured curves across diverse architectures and methods (Average, TA, TIES, DARE), and explains two robust regularities: most gains arrive early, and variability shrinks as more experts are included. Building on this, we present a simple theory that explains why gains fall roughly as 1/k and links the floor and tail to properties of the base model and the diversity across domains. This law enables predictive planning: estimate how many experts are needed to reach a target loss, decide when to stop adding experts, and trade off scaling the base model versus adding experts under a fixed budget--turning merging from heuristic practice into a computationally efficient, planable alternative to multitask training. This suggests a scaling principle for distributed generative AI: predictable gains can be achieved by composing specialists, offering a complementary path toward AGI-level systems.

cs.AI↗
arXiv2026

Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training

Machine-generated text (MGT) detection is critical for regulating online information ecosystems, yet existing detectors often underperform in few-shot settings and remain vulnerable to adversarial, humanizing attacks. To build accurate and robust detectors under limited supervision, we adopt a threat-modeling perspective and study detector vulnerabilities from an attacker's viewpoint under an output-only black-box setting. Motivated by this perspective, we propose RAG-GuidEd Attacker Strengthens ConTrastive Few-shot Detector (REACT), an adversarial training framework that improves both few-shot detection performance and robustness against attacks. REACT couples a humanization-oriented attacker with a target detector: the attacker leverages retrieval-augmented generation (RAG) to craft highly human-like adversarial examples to evade detection, while the detector learns from these adversaries with a contrastive objective to stabilize few-shot representation learning and enhance robustness. We alternately update the attacker and the detector to enable their co-evolution. Experiments on 4 datasets with 4 shot sizes and 3 random seeds show that REACT improves average detection F1 by 4.95 points over 8 state-of-the-art (SOTA) detectors and reduces the average attack success rate (ASR) under 4 strong attacks by 3.66 percentage points.

cs.CR↗
arXiv2026

MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors

We present MGTEVAL, an extensible platform for systematic evaluation of Machine-Generated Text (MGT) detectors. Despite rapid progress in MGT detection, existing evaluations are often fragmented across datasets, preprocessing, attacks, and metrics, making results hard to compare and reproduce. MGTEVAL organizes the workflow into four components: Dataset Building, Dataset Attack, Detector Training, and Performance Evaluation. It supports constructing custom benchmarks by generating MGT with configurable LLMs, applying 12 text attacks to test sets, training detectors via a unified interface, and reporting effectiveness, robustness, and efficiency. The platform provides both command-line and Web-based interfaces for user-friendly experimentation without code rewriting.

cs.CR↗
arXiv2026

Gaze to Insight: A Scalable AI Approach for Detecting Gaze Behaviours in Face-to-Face Collaborative Learning

Previous studies have illustrated the potential of analysing gaze behaviours in collaborative learning to provide educationally meaningful information for students to reflect on their learning. Over the past decades, machine learning approaches have been developed to automatically detect gaze behaviours from video data. Yet, since these approaches often require large amounts of labelled data for training, human annotation remains necessary. Additionally, researchers have questioned the cross-configuration robustness of machine learning models developed, as training datasets often fail to encompass the full range of situations encountered in educational contexts. To address these challenges, this study proposes a scalable artificial intelligence approach that leverages pretrained and foundation models to automatically detect gaze behaviours in face-to-face collaborative learning contexts without requiring human-annotated data. The approach utilises pretrained YOLO11 for person tracking, YOLOE-26 with text-prompt capability for education-related object detection, and the Gaze-LLE model for gaze target prediction. The results indicate that the proposed approach achieves an F1-score of 0.829 in detecting students' gaze behaviours from video data, with strong performance for laptop-directed gaze and peer-directed gaze, yet weaker performance for other gaze targets. Furthermore, when compared to other supervised machine learning approaches, the proposed method demonstrates superior and more stable performance in complex contexts, highlighting its better cross-configuration robustness. The implications of this approach for supporting students' collaborative learning in real-world environments are also discussed.

cs.CV↗
arXiv2026

CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models

Vision-language models (VLMs) achieve strong performance on many benchmarks, yet a basic reliability question remains underexplored: when visual evidence conflicts with commonsense, do models follow what is shown or what commonsense suggests? A characteristic failure in this setting is that the model overrides visual evidence and outputs the commonsense alternative. We term this phenomenon \textbf{commonsense-driven hallucination} (CDH). To evaluate it, we introduce \textbf{CDH-Bench}, a benchmark designed to create explicit \textbf{visual evidence--commonsense conflicts}. CDH-Bench covers three dimensions: \textit{counting anomalies}, \textit{relational anomalies}, and \textit{attribute anomalies}. We evaluate frontier VLMs under \textit{binary Question Answering (QA)} and \textit{multiple-choice QA}, and report metrics including \textit{Counterfactual Accuracy} (CF-Acc), \textit{Commonsense Accuracy} (CS-Acc), \textit{Counterfactual Accuracy Drop} (CFAD), \textit{Commonsense Collapse Rate} (CCR), and \textit{Relative Prior Dependency} (RPD). Results show that even strong models remain vulnerable to prior-driven normalization under visual evidence--commonsense conflict. CDH-Bench provides a controlled diagnostic of visual fidelity under visual evidence--commonsense conflict.

cs.CV↗
arXiv2026

Quasiperiodic Elliptic Operators: Projection Method and Convergence Analysis

Quasiperiodic elliptic operators (QEOs) serve as fundamental models in both mathematics and physics, as exemplified by their role in the numerical modeling of one-dimensional photonic quasicrystals. However, distinct from periodic elliptic operators, approximating eigenpairs for QEOs poses significant challenges, particularly in capturing the full spectral structure (notably the continuous spectrum) and deriving convergence guarantees in the absence of compactness. In this paper, we develop a high-accuracy numerical method to compute eigenpairs of QEOs based on the projection method, which embeds quasiperiodic operators into a higher-dimensional periodic torus. To address the non-compactness issue, we construct a directional-derivative Hilbert space along irrational manifolds of a high-dimensional torus and characterize operators equivalent to QEOs within this space. By integrating spectral theory for non-compact operators into the Babuška-Osborn eigenproblem framework, we establish rigorous convergence analysis and prove that our method achieves spectral accuracy. Numerical experiments validate the accuracy and efficiency of the proposed method, including a one-dimensional photonic quasicrystal and two- and three-dimensional QEOs.

math.NA↗
arXiv2026

A Novel Immune Algorithm for Multiparty Multiobjective Optimization

Traditional multiobjective optimization problems (MOPs) are insufficiently equipped for scenarios involving multiple decision makers (DMs), which are prevalent in many practical applications. These scenarios are categorized as multiparty multiobjective optimization problems (MPMOPs). For MPMOPs, the goal is to find a solution set that is as close to the Pareto front of each DM as much as possible. This poses challenges for evolutionary algorithms in terms of searching and selecting. To better solve MPMOPs, this paper proposes a novel approach called the multiparty immune algorithm (MPIA). The MPIA incorporates an inter-party guided crossover strategy based on the individual's non-dominated sorting ranks from different DM perspectives and an adaptive activation strategy based on the proposed multiparty cover metric (MCM). These strategies enable MPIA to activate suitable individuals for the next operations, maintain population diversity from different DM perspectives, and enhance the algorithm's search capability. To evaluate the performance of MPIA, we compare it with ordinary multiobjective evolutionary algorithms (MOEAs) and state-of-the-art multiparty multiobjective optimization evolutionary algorithms (MPMOEAs) by solving synthetic multiparty multiobjective problems and real-world biparty multiobjective unmanned aerial vehicle path planning (BPUAV-PP) problems involving multiple DMs. Experimental results demonstrate that MPIA outperforms other algorithms.

cs.NE↗
arXiv2026

Spectral convergence of sum-of-Gaussians tensor neural networks for many-electron Schrödinger equation

We present an improved version of the sum-of-Gaussians tensor neural network (SOG-TNN) architecture for solving many-electron Schrödinger equation for one-dimensional soft-Coulomb systems. Model reduction techniques are introduced to reduce the number of tensor-factorized bases under the SOG approximation of the kernel. The Slater determinant ansatz is employed so that the anti-symmetric property of the wave function can be strictly preserved. Numerical results show that the SOG-TNN achieves high accuracy with remarkably small basis sizes. Robust spectral convergence with respect to the basis size is also observed, consistently characterized by a mixed algebraic-exponential model for the error decay. These findings validate that the SOG-TNN architecture provides an ultra-efficient and low-rank representation of complex multi-electron wave functions, shedding light on high-fidelity quantum calculations in larger-scale many-electron systems.

physics.chem-ph↗
arXiv2026

Sex chromosome stability and turnover across vertebrates: a developmental gene regulatory network perspective

Sex chromosomes have evolved repeatedly across the Tree of Life, yet their evolutionary fates differ strikingly. In sharp contrast to mammals and birds with degenerated, stable Y/W chromosomes, in most amphibians, teleosts, non avian reptiles and flowering plants, sex chromosomes remain largely homomorphic and undergo frequently turnover. Explanations such as the evolutionary trap hypothesis, sexually antagonistic selection, mutation load, genetic drift and selfish genetic elements, focus on population genetic processes and do not fully explain this pattern. Here we propose the developmental gene regulatory network (GRN) lock in hypothesis. We compile case studies of turnover across vertebrates, synthesise comparative developmental data on sex determination and dosage regulation (DC). In mammals and birds, sex is determined by an early, initiation by somatic cells, fully penetrant master signal acting within a narrow, thermally buffered embryonic window. This signal operates within highly canalised GRNs, coupled to chromosome scale dosage compensation, with alternative splicing events playing little or no causal role in primary sex determination. This configuration makes it difficult for new master sex determining loci to invade without generating deleterious intermediate states. By contrast, many ectothermic vertebrates possess flexible, integrative threshold GRNs in which genetic, germ cells and environmental inputs interact over a prolonged sensitive embryonic period, with absent or largely gene-by-gene based DC and environmentally responsive splicing near key regulatory nodes, providing many entry points for sex determining loci to evolve. We outline empirical predictions and highlight how integrating developmental biology, molecular mechanisms and population genetics can yield testable models for when sex chromosomes become evolutionarily locked-in versus repeated turnover.

q-bio.PE↗
arXiv2026

Sum-of-Gaussians tensor neural networks for high-dimensional Schrödinger equation

We propose an accurate, efficient, and low-memory sum-of-Gaussians tensor neural network (SOG-TNN) algorithm for solving the high-dimensional Schrödinger equation. The SOG-TNN utilizes a low-rank tensor product representation of the solution to overcome the curse of dimensionality associated with high-dimensional integration. To handle the Coulomb interaction, we introduce an SOG decomposition to approximate the interaction kernel such that it is dimensionally separable, leading to a tensor representation with rapid convergence. We further develop a range-splitting scheme that partitions the Gaussian terms into short-, long-, and mid-range components. They are treated with the asymptotic expansion, the low-rank Chebyshev expansion, and the model reduction with singular-value decomposition, respectively, significantly reducing the number of two-dimensional integrals in computing electron-electron interactions. The SOG decomposition well resolves the computational challenge due to the singularity of the Coulomb interaction, leading to an efficient algorithm for the high-dimensional problem under the TNN framework. Numerical results demonstrate the outstanding performance of the new method, revealing that the SOG-TNN is a promising way for accurately tackling quantum systems.

physics.comp-ph↗
arXiv2026

Random batch sum-of-Gaussians method for molecular dynamics simulation of particle systems in the NPT ensemble

In this work, we develop a random batch sum-of-Gaussians (RBSOG) method for molecular dynamics simulations of charged systems in the isothermal-isobaric (NPT) ensemble. We introduce an SOG splitting of the pressure-related $1/r^3$ kernel, yielding a smooth short-/long-range decomposition for instantaneous pressure evaluation. The long-range part is treated in Fourier space by random-batch importance sampling. Because the radial and non-radial pressure components favor different proposals, direct sampling either increases structure-factor evaluations and communication or leads to substantial variance inflation. To address this tradeoff, we introduce a measure-recalibration strategy that reuses Fourier modes drawn from the radial proposal and corrects them for the non-radial target, producing an unbiased pressure estimator with significantly reduced variance and negligible extra cost. The resulting method mitigates pressure artifacts caused by cutoff discontinuities in traditional Ewald-based treatments while preserving near-optimal $O(N)$ complexity. We provide theoretical evidence on pressure decomposition error, consistency of stochastic approximation, and convergence of RBSOG-based MD. Numerical experiments on bulk water, LiTFSI ionic liquids, and DPPC membranes show that RBSOG accurately reproduces key structural and dynamical observables with small batch sizes ($P\sim 100$). In large-scale benchmarks up to $10^7$ atoms on $2048$ CPU cores, RBSOG achieves about an order-of-magnitude speedup over particle-particle particle-mesh in electrostatic calculations for NPT simulations, together with a consistent $4\times$ variance reduction relative to random batch Ewald and excellent weak/strong scalability. Overall, RBSOG provides a practical and scalable route to reduce time-to-solution and communication cost in large-scale NPT simulations.

physics.comp-ph↗
arXiv2026

Coherent and Multi-modality Image Inpainting via Latent Space Optimization

With the advancements in denoising diffusion probabilistic models (DDPMs), image inpainting has significantly evolved from merely filling information based on nearby regions to generating content conditioned on various prompts such as text, exemplar images, and sketches. However, existing methods, such as model fine-tuning and simple concatenation of latent vectors, often result in generation failures due to overfitting and inconsistency between the inpainted region and the background. In this paper, we argue that the current large diffusion models are sufficiently powerful to generate realistic images without further tuning. Hence, we introduce PILOT (in\textbf{P}ainting v\textbf{I}a \textbf{L}atent \textbf{O}p\textbf{T}imization), an optimization approach grounded on a novel \textit{semantic centralization} and \textit{background preservation loss}. Our method searches latent spaces capable of generating inpainted regions that exhibit high fidelity to user-provided prompts while maintaining coherence with the background. Furthermore, we propose a strategy to balance optimization expense and image quality, significantly enhancing generation efficiency. Our method seamlessly integrates with any pre-trained model, including ControlNet and DreamBooth, making it suitable for deployment in multi-modal editing tools. Our qualitative and quantitative evaluations demonstrate that PILOT outperforms existing approaches by generating more coherent, diverse, and faithful inpainted regions in response to provided prompts.

cs.CV↗
arXiv2026

The fundamental localization phases in quasiperiodic systems: A unified framework and exact results

The disordered quantum systems host three classes of quantum states, the extended, localized, and critical, which bring up seven distinct fundamental phases in nature: three pure phases and four coexisting ones with mobility edges, yet a unified theory built on universal mechanism and full realization of all these phases has not been developed. Here we propose a unified framework based on a spinful quasiperiodic (QP) system which realizes all the fundamental localization phases, with the exact and universal results being obtained for their characterization. First, we show that the pure phases are obtained when the chiral(-like) symmetry preserves in the proposed spinful QP model, giving a criterion for emergence of the pure phases and otherwise the coexisting ones. Further, we uncover a novel mechanism for the critical states that their emergence is protected by the generalized incommensurate matrix element zeros in the spinful QP model, which considerably broadens rigorous realizations of the exotic critical states. We then show criteria of exact solvability for the present spinful QP system, with which we construct various exactly solvable models for all distinct localization phases. In particular, we propose two novel models, dubbed spin-selective QP lattice model and QP optical Raman lattice model, to achieve all basic types of mobility edges and all the seven fundamental phases of Anderson localization physics, respectively. The experimental scheme is proposed and studied in detail to realize these models with high feasibility. This study establishes a complete and profound theoretical framework which enables an in-depth exploration of the broad classes of all fundamental localization phenomena in QP systems, and offers key insights for constructing their exactly solvable models with experimental feasibility.

cond-mat.dis-nn↗