arXiv subjects

Ming Zhong

Publications and source records attributed to Ming Zhong.

At least 55 records · Page 3Linked to original sources

arXiv2025

EgoLCD: Egocentric Video Generation with Long Context Diffusion

Generating long, coherent egocentric videos is difficult, as hand-object interactions and procedural tasks require reliable long-term memory. Existing autoregressive models suffer from content drift, where object identity and scene semantics degrade over time. To address this challenge, we introduce EgoLCD, an end-to-end framework for egocentric long-context video generation that treats long video synthesis as a problem of efficient and stable memory management. EgoLCD combines a Long-Term Sparse KV Cache for stable global context with an attention-based short-term memory, extended by LoRA for local adaptation. A Memory Regulation Loss enforces consistent memory usage, and Structured Narrative Prompting provides explicit temporal guidance. Extensive experiments on the EgoVid-5M benchmark demonstrate that EgoLCD achieves state-of-the-art performance in both perceptual quality and temporal consistency, effectively mitigating generative forgetting and representing a significant step toward building scalable world models for embodied AI. Code: https://github.com/AIGeeksGroup/EgoLCD. Website: https://aigeeksgroup.github.io/EgoLCD.

cs.CV↗

arXiv2025

Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question Answering

LLMs often suffer from hallucinations and outdated or incomplete knowledge. RAG is proposed to address these issues by integrating external knowledge like that in KGs into LLMs. However, leveraging private KGs in RAG systems poses significant privacy risks due to the black-box nature of LLMs and potential insecure data transmission, especially when using third-party LLM APIs lacking transparency and control. In this paper, we investigate the privacy-protected RAG scenario for the first time, where entities in KGs are anonymous for LLMs, thus preventing them from accessing entity semantics. Due to the loss of semantics of entities, previous RAG systems cannot retrieve question-relevant knowledge from KGs by matching questions with the meaningless identifiers of anonymous entities. To realize an effective RAG system in this scenario, two key challenges must be addressed: (1) How can anonymous entities be converted into retrievable information. (2) How to retrieve question-relevant anonymous entities. Hence, we propose a novel ARoG framework including relation-centric abstraction and structure-oriented abstraction strategies. For challenge (1), the first strategy abstracts entities into high-level concepts by dynamically capturing the semantics of their adjacent relations. It supplements meaningful semantics which can further support the retrieval process. For challenge (2), the second strategy transforms unstructured natural language questions into structured abstract concept paths. These paths can be more effectively aligned with the abstracted concepts in KGs, thereby improving retrieval performance. To guide LLMs to effectively retrieve knowledge from KGs, the two strategies strictly protect privacy from being exposed to LLMs. Experiments on three datasets demonstrate that ARoG achieves strong performance and privacy-robustness.

cs.CL↗

arXiv2025

A Compilation Framework for Quantum Circuits with Mid-Circuit Measurement Error Awareness

Mid-circuit measurement (MCM) provides the capability for qubit reuse and dynamic control in quantum processors, enabling more resource-efficient algorithms and supporting error-correction procedures. However, MCM introduces several sources of error, including measurement-induced crosstalk, idling-qubit decoherence, and reset infidelity, and these errors exhibit pronounced qubit-dependent variability within a single device. Since existing compilers such as the Qiskit-compiler and QR-Map (the state-of-art qubit reuse compiler) do not account for this variability, circuits with frequent MCM operations often experience substantial fidelity loss. In thie paper, we propose MERA, a compilation framework that performs MCM-error-aware layout, routing, and scheduling. MERA leverages lightweight profiling to obtain a stable per-qubit MCM error distribution, which it uses to guide error-aware qubit mapping and SWAP insertions. To further mitigate MCM-related decoherence and crosstalk, MERA augments as-late-as-possible scheduling with context-aware dynamic decoupling. Evaluated on 27 benchmark circuits, MERA achieves 24.94% -- 52.00% fidelity improvement over the Qiskit compiler (optimization level 3) without introducing additional overhead. On QR-Map-generated circuits, it improves fidelity by 29.26% on average and up to 122.58% in the best case, demonstrating its effectiveness for dynamic circuits dominated by MCM operations.

quant-ph↗

arXiv2025

Unified Learning of the Profile Function in Discrete Keller-Segel Models

We propose a unified learning framework for identifying the profile function in discrete Keller-Segel equations, which are widely used mathematical models for understanding chemotaxis. Training data are obtained via either a rigorously developed particle method designed for stable simulation of high-dimensional Keller-Segel systems, or stochastic differential equations approximating the continuous Keller-Segel PDE. Our approach addresses key challenges, including data instability in dimensions higher than two and the accurate capture of singular behavior in the profile function. Additionally, we introduce an adaptive learning strategy to enhance performance. Extensive numerical experiments are presented to validate the effectiveness of our method.

math.NA↗

arXiv2025

AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science

Large language models (LLMs) have advanced the automation of data science workflows. Yet it remains unclear whether they can critically leverage external domain knowledge as human data scientists do in practice. To answer this question, we introduce AssistedDS (Assisted Data Science), a benchmark designed to systematically evaluate how LLMs handle domain knowledge in tabular prediction tasks. AssistedDS features both synthetic datasets with explicitly known generative mechanisms and real-world Kaggle competitions, each accompanied by curated bundles of helpful and adversarial documents. These documents provide domain-specific insights into data cleaning, feature engineering, and model selection. We assess state-of-the-art LLMs on their ability to discern and apply beneficial versus harmful domain knowledge, evaluating submission validity, information recall, and predictive performance. Our results demonstrate three key findings: (1) LLMs frequently exhibit an uncritical adoption of provided information, significantly impairing their predictive performance when adversarial content is introduced, (2) helpful guidance is often insufficient to counteract the negative influence of adversarial information, and (3) in Kaggle datasets, LLMs often make errors in handling time-series data, applying consistent feature engineering across different folds, and interpreting categorical variables correctly. These findings highlight a substantial gap in current models' ability to critically evaluate and leverage expert knowledge, underscoring an essential research direction for developing more robust, knowledge-aware automated data science systems. Our data and code are publicly available here: https://github.com/jeremyxianx/Assisted-DS

cs.LG↗

arXiv2025

Efficient High-Accuracy PDEs Solver with the Linear Attention Neural Operator

Neural operators offer a powerful data-driven framework for learning mappings between function spaces, in which the transformer-based neural operator architecture faces a fundamental scalability-accuracy trade-off: softmax attention provides excellent fidelity but incurs quadratic complexity $\mathcal{O}(N^2 d)$ in the number of mesh points $N$ and hidden dimension $d$, while linear attention variants reduce cost to $\mathcal{O}(N d^2)$ but often suffer significant accuracy degradation. To address the aforementioned challenge, in this paper, we present a novel type of neural operators, Linear Attention Neural Operator (LANO), which achieves both scalability and high accuracy by reformulating attention through an agent-based mechanism. LANO resolves this dilemma by introducing a compact set of $M$ agent tokens $(M \ll N)$ that mediate global interactions among $N$ tokens. This agent attention mechanism yields an operator layer with linear complexity $\mathcal{O}(MN d)$ while preserving the expressive power of softmax attention. Theoretically, we demonstrate the universal approximation property, thereby demonstrating improved conditioning and stability properties. Empirically, LANO surpasses current state-of-the-art neural PDE solvers, including Transolver with slice-based softmax attention, achieving average $19.5\%$ accuracy improvement across standard benchmarks. By bridging the gap between linear complexity and softmax-level performance, LANO establishes a scalable, high-accuracy foundation for scientific machine learning applications.

cs.LG↗

arXiv2025

Asymmetric integrable turbulence and rogue wave statistics for the derivative nonlinear Schrödinger equation

We investigate the asymmetric integrable turbulence and rogue waves (RWs) emerging from the modulation instability (MI) of plane waves for the DNLS equation. The $n$-th moments and ensemble-averaged kinetic and potential energy exhibit oscillatory convergence towards their steady-state values. Specifically, the amplitudes of oscillations for these indexes decay asymptotically with time as $t^{-1.36}$, while the phase shifts demonstrate a nonlinear decay with a rate of $t^{-0.78}$. The frequency of these oscillations is observed to be twice the maximum growth rate of MI. These oscillations can be classified into two distinct types: one is in phase with ensemble-averaged potential energy modulus $|\langle H_4\rangle|$, and the other is anti-phase. At the same time, this unity is also reflected in the wave-action spectrum $ S_k(t) $ for a given $ k $, the auto-correlation function $ g(x,t) $ for a given $ x $, as well as the PDF $ P(I,t) $. The critical feature of the turbulence is the wave-action spectrum, which follows a power-law distribution of $ |k+3|^{-α} $ expect for $k=-3$. Unlike the NLS equation, the turbulence in the DNLS setting is asymmetric, primarily due to the asymmetry between the wave number of the plane wave from the MI and the perturbation wave number.. As the asymptotic peak value of $ S_k $ is observed at $ k = -3 $, the auto-correlation function exhibits a nonzero level as $ x \to \pm L/2 $. The PDF of the wave intensity asymptotically approaches the exponential distribution in an oscillatory manner. However, during the initial stage of the nonlinear phase, MI slightly increases the occurrence of RWs. This happens at the moments when the potential modulus is at its minimum, where the probability of RWs occurring in the range of $ I\in [12, 15] $ is significantly higher than in the asymptotic steady state.

nlin.SI↗

arXiv2025

CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization

Multimodal large language models (MLLMs) rely heavily on instruction tuning to align vision and language capabilities, yet the computational cost of training on large-scale datasets remains a major bottleneck. Existing data selection methods aim to mitigate this by selecting important and diverse subsets, but they often suffer from two critical drawbacks: high computational overhead from processing the entire dataset and suboptimal data selection due to separate treatment of importance and diversity. We introduce CoIDO, a novel dual-objective framework that jointly optimizes data importance and diversity to overcome these challenges. Unlike existing approaches that require costly evaluations across the whole dataset, CoIDO employs a lightweight plug-in scorer. This scorer is trained on just a small random sample of data to learn the distribution of the candidate set, drastically reducing computational demands. By leveraging a homoscedastic uncertainty-based formulation, CoIDO effectively balances importance and diversity during training, enabling efficient and scalable data selection. In our experiments, we trained the CoIDO scorer using only 20 percent of randomly sampled data. Once trained, CoIDO was applied to the entire dataset to select a 20 percent subset for instruction tuning. On the widely used LLaVA-1.5-7B model across ten downstream tasks, this selected subset achieved an impressive 98.2 percent of the performance of full-data fine-tuning, on average.

cs.CV↗

arXiv2025

Robustness of One-to-Many Interdependent Higher-order Networks Against Cascading Failures

In the real world, the stable operation of a network is usually inseparable from the mutual support of other networks. In such an interdependent network, a node in one layer may depend on multiple nodes in another layer, forming a complex one-to-many dependency relationship. Meanwhile, there may also be higher-order interactions between multiple nodes within a layer, which increases the connectivity within the layer. However, existing research on one-to-many interdependence often neglects intra-layer higher-order structures and lacks a unified theoretical framework for inter-layer dependencies. Moreover, current research on interdependent higher-order networks typically assumes idealized one-to-one inter-layer dependencies, which does not reflect the complexity of real-world systems. These limitations hinder a comprehensive understanding of how such networks withstand failures. Therefore, this paper investigates the robustness of one-to-many interdependent higher-order networks under random attacks. Depending on whether node survival requires at least one dependency edge or multiple dependency edges, we propose four inter-layer interdependency conditions and analyze the network's robustness after cascading failures induced by random attacks. Using percolation theory, we establish a unified theoretical framework that reveals how higher-order interaction structures within intra-layers and inter-layer coupling parameters affect network reliability and system resilience. Additionally, we extend our study to partially interdependent hypergraphs. We validate our theoretical analysis on both synthetic and real-data-based interdependent hypergraphs, offering insights into the optimization of network design for enhanced reliability.

cs.SI↗

arXiv2025

A Survey on Retrieval And Structuring Augmented Generation with Large Language Models

Large Language Models (LLMs) have revolutionized natural language processing with their remarkable capabilities in text generation and reasoning. However, these models face critical challenges when deployed in real-world applications, including hallucination generation, outdated knowledge, and limited domain expertise. Retrieval And Structuring (RAS) Augmented Generation addresses these limitations by integrating dynamic information retrieval with structured knowledge representations. This survey (1) examines retrieval mechanisms including sparse, dense, and hybrid approaches for accessing external knowledge; (2) explore text structuring techniques such as taxonomy construction, hierarchical classification, and information extraction that transform unstructured text into organized representations; and (3) investigate how these structured representations integrate with LLMs through prompt-based methods, reasoning frameworks, and knowledge embedding techniques. It also identifies technical challenges in retrieval efficiency, structure quality, and knowledge integration, while highlighting research opportunities in multimodal retrieval, cross-lingual structures, and interactive systems. This comprehensive overview provides researchers and practitioners with insights into RAS methods, applications, and future directions.

cs.CL↗

arXiv2025

A Survey on Training-free Alignment of Large Language Models

The alignment of large language models (LLMs) aims to ensure their outputs adhere to human values, ethical standards, and legal norms. Traditional alignment methods often rely on resource-intensive fine-tuning (FT), which may suffer from knowledge degradation and face challenges in scenarios where the model accessibility or computational resources are constrained. In contrast, training-free (TF) alignment techniques--leveraging in-context learning, decoding-time adjustments, and post-generation corrections--offer a promising alternative by enabling alignment without heavily retraining LLMs, making them adaptable to both open-source and closed-source environments. This paper presents the first systematic review of TF alignment methods, categorizing them by stages of pre-decoding, in-decoding, and post-decoding. For each stage, we provide a detailed examination from the viewpoint of LLMs and multimodal LLMs (MLLMs), highlighting their mechanisms and limitations. Furthermore, we identify key challenges and future directions, paving the way for more inclusive and effective TF alignment techniques. By synthesizing and organizing the rapidly growing body of research, this survey offers a guidance for practitioners and advances the development of safer and more reliable LLMs.

cs.CL↗

arXiv2025

The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

Large Language Models (LLMs) achieve gold-medal performance across many benchmarks, yet it remains unclear whether such success reflects genuine reasoning or pattern matching. From a cognitive science perspective, an informative test is whether models can master an unfamiliar language through explicit metalinguistic deductive learning, a paradigm where human learners can reliably internalise grammatical systems through metalinguistic reasoning. We address this question with Camlang, a novel constructed language that exhibits naturalistic yet unattested feature combinations. Camlang consists of two explicit resources, a grammar book and a bilingual dictionary, which mirror adult second-language learning via explicit grammar rules and lexical lookup, and enable us to disentangle errors in morpho-syntax, lexical semantics, and sentence-level reasoning. Human experiments show that these resources are sufficient for participants to acquire Camlang and successfully solve Camlang tasks. To operationalise evaluation, we adapt CommonsenseQA into Camlang, creating Camlang-CSQA-v0, the first task in a broader suite where solving questions requires applying grammar rules and lexical mappings. Experimental results show that GPT-5 achieves 98\% EM accuracy in English but only 47\% in Camlang, far below human performance at 87\%, while other state-of-the-art reasoning LLMs perform even worse. Human verification further reveals that most model successes stem from shallow lexical alignment while GPT-5 shows emerging metalinguistic awareness to a limited extent but not systematic grammatical mastery as humans. Camlang establishes a cognitively grounded evaluation paradigm that exposes fundamental gaps between current models and human metalinguistic competence.

cs.CL↗

arXiv2025

SEDONA-GesaRaT: an AI-Accelerated Radiative Transfer Program for 3-D Supernova Simulations

We present SEDONA-GesaRaT, a rapid code for supernova radiative transfer simulation developed based on the Monte-Carlo radiative transfer code SEDONA. We use a set of atomic physics neural networks (APNN), an artificial intelligence (AI) solver for the non-local thermodynamic equilibrium (NLTE) atomic physics level population calculation, which is trained and validated on 119 1-D type Ia supernova (SN Ia) radiative transfer simulation results showing great computation speed and accuracy. SEDONA-GesaRaT has been applied to the 3-D SN Ia explosion model N100 to perform a 3-D NLTE radiative transfer calculation. The spatially resolved linear polarization data cubes of the N100 model are successfully retrieved with a high signal-to-noise ratio using the integral-based technique (IBT). The overall computation cost of a 3-D NLTE spectropolarimetry simulation using SEDONA-GesaRaT is only $\sim$3000 core-hours, while the previous codes could only finish 1-D NLTE simulation, or 3-D local thermodynamic equilibrium (LTE) simulation, with similar computation resources. The excellent computing efficiency allows SEDONA-GesaRaT for future large-scale simulations that systematically study the internal structures of supernovae.

astro-ph.HE↗

arXiv2025

Aligning VLM Assistants with Personalized Situated Cognition

Vision-language models (VLMs) aligned with general human objectives, such as being harmless and hallucination-free, have become valuable assistants of humans in managing visual tasks. However, people with diversified backgrounds have different cognition even in the same situation. Consequently, they may have personalized expectations for VLM assistants. This highlights the urgent need to align VLM assistants with personalized situated cognition for real-world assistance. To study this problem, we first simplify it by characterizing individuals based on the sociological concept of Role-Set. Then, we propose to evaluate the individuals' actions to examine whether the personalized alignment is achieved. Further, we construct a benchmark named PCogAlignBench, which includes 18k instances and 20 individuals with different Role-Sets. Finally, we present a framework called PCogAlign, which constructs a cognition-aware and action-based reward model for personalized alignment. Experimental results and human evaluations demonstrate the reliability of the PCogAlignBench and the effectiveness of our proposed PCogAlign. We will open-source the constructed benchmark and code at https://github.com/NLPGM/PCogAlign.

cs.AI↗

arXiv2025

Toxicity Detection towards Adaptability to Changing Perturbations

Toxicity detection is crucial for maintaining the peace of the society. While existing methods perform well on normal toxic contents or those generated by specific perturbation methods, they are vulnerable to evolving perturbation patterns. However, in real-world scenarios, malicious users tend to create new perturbation patterns for fooling the detectors. For example, some users may circumvent the detector of large language models (LLMs) by adding `I am a scientist' at the beginning of the prompt. In this paper, we introduce a novel problem, i.e., continual learning jailbreak perturbation patterns, into the toxicity detection field. To tackle this problem, we first construct a new dataset generated by 9 types of perturbation patterns, 7 of them are summarized from prior work and 2 of them are developed by us. We then systematically validate the vulnerability of current methods on this new perturbation pattern-aware dataset via both the zero-shot and fine tuned cross-pattern detection. Upon this, we present the domain incremental learning paradigm and the corresponding benchmark to ensure the detector's robustness to dynamically emerging types of perturbed toxic text. Our code and dataset are provided in the appendix and will be publicly available at GitHub, by which we wish to offer new research opportunities for the security-relevant communities.

cs.CR↗

arXiv2025

Learning Stochastic Dynamical Systems with Structured Noise

Stochastic differential equations (SDEs) are a ubiquitous modeling framework that finds applications in physics, biology, engineering, social science, and finance. Due to the availability of large-scale data sets, there is growing interest in learning mechanistic models from observations with stochastic noise. In this work, we present a nonparametric framework to learn both the drift and diffusion terms in systems of SDEs where the stochastic noise is singular. Specifically, inspired by second-order equations from classical physics, we consider systems which possess structured noise, i.e. noise with a singular covariance matrix. We provide an algorithm for constructing estimators given trajectory data and demonstrate the effectiveness of our methods via a number of examples from physics and biology. As the developed framework is most naturally applicable to systems possessing a high degree of dimensionality reduction (i.e. symmetry), we also apply it to the high dimensional Cucker-Smale flocking model studied in collective dynamics and show that it is able to accurately infer the low dimensional interaction kernel from particle data.

stat.ML↗

arXiv2025

Multimodal Search in Chemical Documents and Reactions

We present a multimodal search tool that facilitates retrieval of chemical reactions, molecular structures, and associated text from scientific literature. Queries may combine molecular diagrams, textual descriptions, and reaction data, allowing users to connect different representations of chemical information. To support this, the indexing process includes chemical diagram extraction and parsing, extraction of reaction data from text in tabular form, and cross-modal linking of diagrams and their mentions in text. We describe the system's architecture, key functionalities, and retrieval process, along with expert assessments of the system. This demo highlights the workflow and technical components of the search system.

cs.IR↗

arXiv2024

Two-dimensional fractional discrete NLS equations: dispersion relations, rogue waves, fundamental and vortex solitons

We introduce physically relevant new models of two-dimensional (2D) fractional lattice media accounting for the interplay of fractional intersite coupling and onsite self-focusing. Our approach features novel discrete fractional operators based on an appropriately modified definition of the continuous Riesz fractional derivative. The model of the 2D isotropic lattice employs the discrete fractional Laplacian, whereas the 2D anisotropic system incorporates discrete fractional derivatives acting independently along orthogonal directions with different Lévy indices (LIs). We derive exact linear dispersion relations (DRs), and identify spectral bands that permit linear modes to exist, finding them to be similar to their continuous counterparts, apart from differences in the wavenumber range. Additionally, the modulational instability in the discrete models is studied in detail, and, akin to the linear DRs, it is found to align with the situation in continuous models. This consistency highlights the nature of our newly defined discrete fractional derivatives. Furthermore, using Gaussian inputs, we produce a variety of rogue-wave structures. By means of numerical methods, we systematically construct families of 2D fundamental and vortex solitons, and examine their stability. Fundamental solitons maintain the stability due to the discrete nature of the interactions, preventing the onset of the critical and supercritical collapse. On the other hand, vortex solitons are unstable in the isotropic lattice model. However, the anisotropic one -- in particular, its symmetric version with equal LIs acting in both directions -- maintains stable vortex solitons with winding numbers $S=1$ and $S=3$. The detailed results stress the robustness of the newly defined discrete fractional Laplacian in supporting well-defined soliton modes in the 2D lattice media.

nlin.PS↗