arXiv subjects

Ming Zhong

Publications and source records attributed to Ming Zhong.

At least 19 recordsLinked to original sources

arXiv2026

Label Propagation for Physics-Informed Neural Networks and Physics-Informed Gaussian Processes

We present a series of empirical results of the application of semi-supervised label propagation techniques in training physics-informed machine learning methods. This includes self-training of physics-informed neural networks and physics-informed Gaussian processes in isolation, and the integration of the two via co-training, therefore establishing a hybrid between these two main classes of physics-informed machine learning. We demonstrate via extensive numerical experiments how these methods can ameliorate the issue of propagating information from boundaries into the physical domain, including information from initial conditions in the case of solving stiff time-dependent partial differential equations, which is known to be a common failure mode of physics-informed machine learning.

cs.LG↗

arXiv2026

Learning Interaction Kernels from Collective Steady States

We propose a learning procedure for system identification in interacting particle systems from single-snapshot observations of collective behaviors, unlike existing approaches that rely on observations of trajectories. This setting leads to a fundamentally ill-posed inverse problem, which we solve by using a regularization strategy based on the empirical distribution of observed configurations, drawn from different, unobserved initial conditions. We test our learning procedure on a variety of representative models with steady-state and quasi-stationary patterns, where collective behaviors encode implicit information about the interaction mechanisms, demonstrating that our approach enables stable and accurate recovery of the underlying interaction laws, leading to faithful reproduction of the collective behavior, and in many cases even of the dynamics leading up to it.

stat.ML↗

arXiv2026

Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering

Table Question Answering (TableQA) aims to reason over tables to answer user queries. Existing research treats all questions uniformly and evaluates solely through overall accuracy, obscuring a critical reality that LLMs excel at simple lookups yet struggle with complex operations like aggregation and arithmetic. To reveal this disparity, we introduce a novel \emph{Operation-wise TableQA} task with a fine-grained question taxonomy and release two datasets named WikiTQ-ow and TabFact-ow for evaluation. As for modeling bottlenecks, existing methods flatten tables into linearized texts, disrupting inherent structures and inducing the ``lost-in-the-middle'' issue, which poses a primary barrier to complex cross-row reasoning. Moreover, they typically reason from scratch, neglecting reusable patterns shared across similar operations. To address these limitations, we propose a Skill-augmented Table Graph Reasoning (SkillTGR) framework for self-evolving structured reasoning. Specifically, SkillTGR represents tables as attributed graphs with explicit row-column-cell structures, where LLMs plan and execute dynamic chains to retrieve evidence subgraphs for graph traversal reasoning. Based on this, SkillTGR builds a hierarchical SkillBank to distill reason trajectories into abstract skills under cognitive heuristics, then hybrid retrieves both successful and failed skills for contrastive augmented table graph reasoning, thereby enabling the continual self-evolution. Extensive experiments demonstrate that SkillTGR achieves superior performance with an average of 5.91\% overall and 5.06\% operation-wise improvement, also reducing 19.76\% token consumption and 27.64\% inference latency. Our codes and data will be released upon publication.

cs.AI↗

arXiv2026

Physics Informed Random Feature Neural Networks for Solving PDEs

Machine learning-based partial differential equations (PDEs) solvers have attracted significant attention in recent years. Most progress in this area has been driven by deep neural networks such as physics-informed neural networks (PINNs) and kernel method (such as physics-informed Gaussian Processes). We introduce a physics-informed random feature method for countering part of the spectral bias which PINN-based solvers are facing for a certain class of PDEs. Random feature method was originally proposed to approximate large-scale kernel machines and can be viewed as a specialized randomized neural network. Compared to other state-of-the-art PINN-based solvers which require a large number of collocation points, our proposed method reduces the computational complexity. In this paper, we develop a rigorous approximation error analysis and derive high-probability error bounds on the $H^1$ norm. We provide extensive numerical tests for verifying our theoretical guarantees on error decay rates, as well as several comparison tests to showcase our claimed capability for combating spectral bias in these deep learning based methods.

math.NA↗

arXiv2026

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness against malicious attacks, frequent refusal of benign queries, degradation in generated text quality and general task performance, the former two reflecting tensions in robust safety and the latter constituting utility impairment. We attribute these limitations to the coarse-grained layer-wise interventions in existing methods. To resolve this, we propose NeuronTune, a fine-grained framework that pinpoints and modulates sparse neurons to achieve simultaneous safety-utility optimization. Our approach first pinpoints safety-critical and utility-preserving neurons across all layers via attack-aware attribution, then adapts meta-learning to adaptively modulate their activations. Crucially, the intervention scope of NeuronTune is dynamically controlled via neuron inclusion thresholds, providing a flexible mechanism to prioritize either security-critical or utility-priority requirements. Extensive experimental results demonstrate that our method outperforms existing state-of-the-art technologies, achieving superior model safety while maintaining excellent utility.

cs.LG↗

arXiv2026

MoRF-AST: Calibrated Probabilistic Virtual Sensing for Structural Monitoring under Changing Operating Conditions

Probabilistic full-field reconstruction provides uncertainty-aware response evidence for structural reliability assessment, yet inference from sparse and noisy measurements remains underdetermined. Most existing methods overlook shifts between offline training and operational distributions. Under such shifts, posterior intervals may become miscalibrated, causing the reported uncertainty to lose its probabilistic meaning. This study proposes Modal Residual Flow Matching with Context-Conditioned Affine Spread Transport (MoRF-AST) for calibrated structural virtual sensing under changing operating conditions. MoRF constructs an analytic Gaussian reference posterior in normalized modal coordinates and trains a conditional flow only on posterior-whitened residuals. At deployment, AST estimates response scale from historical measurements at installed sensors and uses gated, mean-preserving Bures-Wasserstein transport to adjust posterior spread. On a bridge-deck benchmark, MoRF achieves a posterior-mean normalized root-mean-square error (NRMSE) of 7.20%, compared with 16.1% and 17.9% for two direct conditional flows. Across eight shifted traffic domains, AST reduces MoRF's cross-domain average coverage error from 0.0535 to 0.0236, a 55.9% reduction, while preserving posterior-mean accuracy. The same transport does not improve the tested alternatives in aggregate, showing that calibration gains require its direction to match the base posterior's dispersion bias. MoRF-AST provides a data-efficient framework for probabilistic full-field reconstruction whose uncertainty remains interpretable under scale-dominated operational distribution shifts. More broadly, this work highlights the need to calibrate uncertainty under changing operational distributions, thereby supporting trustworthy probabilistic modeling and reliability-informed decision-making in civil and infrastructure engineering.

cs.CE↗

arXiv2026

Simultaneous inference of environmental and interaction forces in collective dynamics

Collective dynamics arise in a wide range of physical, biological, and engineering applications. Examples include cell migration, swarm robotics, social dynamics, and animal behavior. A defining characteristic of these systems is the emergence of large-scale coordination from local interactions among agents; a fundamental question is thus to understand the local interactions that give rise to the observed emergent dynamics. We are interested in methods for learning interactions generally, which can describe a wide class of physical systems exhibiting collective dynamics defined by an interaction kernel, without a priori assumptions on the analytical form of this kernel (i.e. it is nonparametric). The advantage of this kernel-based approach is that it incorporates the underlying physics of the model (i.e. collective dynamics), which more general equation-learning approaches may ignore, potentially limiting their effectiveness for model accuracy and predictions. In this work, we extend existing variational learning approaches to collective systems with both interaction kernels and environmental/intra-agent forces. The proposed framework simultaneously infers the interaction kernel non-parametrically while learning the environmental force using either semi-parametric or fully nonparametric representations. The methodology is validated on several benchmark models exhibiting synchronization, alignment, attraction-repulsion, and external environmental forces. We also introduce a model-selection procedure based on our nonparametric learning framework to identify models that optimally explain a given set of trajectory observations. By exploiting the feature-identification capability of the learned models, the proposed procedure can distinguish among different collective dynamics frameworks and recover mechanistic interaction mechanisms directly from trajectory data.

cs.LG↗

arXiv2026

A finite element framework for simulating residential burglary in realistic urban geometries

We consider a partial differential equation (PDE) model to predict residential burglary derived from a probabilistic agent-based model through a mean-field limit operation. The PDE model is a nonlinear, coupled system of two equations in two variables (attractiveness of residential sites and density of criminals), similar to the Keller-Segel model for aggregation based on chemotaxis. Unlike previous works, which applied periodic boundary conditions, we enforce boundary conditions that arise naturally from the variational formulation of the PDE problem, i.e., the starting point for the application of a finite element method. These conditions specify the value of the normal derivatives of the system variables at the boundary. For the numerical solution of the PDE problem discretized in time and space, we propose a scheme that decouples the computation of the attractiveness from the computation of the criminal density at each time step, resulting in the solution of two linear algebraic systems per iteration. Through numerous numerical tests, we demonstrate the robustness and computational efficiency of this approach. Leveraging the flexibility allowed by the finite element method, we show results for spatially heterogeneous model parameters and a realistic geometry (city of Chicago). The paper includes a discussion of future perspectives to build multiscale, 'multi-physics' models that can become a tool for the community. The robust and efficient code developed for this paper, which is shared open-source, is intended as the solid base for this broader research program.

math.NA↗

arXiv2026

Stability in Training PINNs for Stiff PDEs: Why Initial Conditions Matter

Training physics-informed neural networks (PINNs) on stiff, time-dependent PDEs remains a fundamental challenge due to optimization instabilities and gradient pathologies. Through a series of rigorous ablation studies and Neural Tangent Kernel (NTK) analysis, we identify that the exact enforcement of initial conditions (ICs) is a decisive factor in stabilizing the training landscape. We present the first systematic ablation of two core strategies: hard initial-condition constrained transformation and self-adaptive loss weighting. Our findings demonstrate that embedding ICs directly into the network architecture provides an implicit time-marching effect, effectively reducing spectral bias and enabling the solution of highly stiff benchmarks, including sharp transitions and high-frequency coupled systems, primarily under periodic boundary conditions, with a Dirichlet extension reported as an additional robustness check. This work provides a scalable framework for developing reliable and physically-consistent neural solvers for complex mechanical systems.

math.NA↗

arXiv2026

VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging

While Multimodal Large Language Models (MLLMs) excel on benchmarks, their processing paradigm differs from the human ability to integrate visual information. Unlike humans who naturally bridge details and high-level concepts, models tend to treat these elements in isolation. Prevailing evaluation protocols often decouple low-level perception from high-level reasoning, overlooking their semantic and causal dependencies, which yields non-diagnostic results and obscures performance bottlenecks. We present VCU-Bridge, a framework that operationalizes a human-like hierarchy of visual connotation understanding: multi-level reasoning that advances from foundational perception through semantic bridging to abstract connotation, with an explicit evidence-to-inference trace from concrete cues to abstract conclusions. Building on this framework, we construct HVCU-Bench, a benchmark for hierarchical visual connotation understanding with explicit, level-wise diagnostics. Comprehensive experiments demonstrate a consistent decline in performance as reasoning progresses to higher levels. We further develop a data generation pipeline for instruction tuning guided by Monte Carlo Tree Search (MCTS) and show that strengthening low-level capabilities yields measurable gains at higher levels. Interestingly, it not only improves on HVCU-Bench but also brings benefits on general benchmarks (average +2.53%), especially with substantial gains on MMStar (+7.26%), demonstrating the significance of the hierarchical thinking pattern and its effectiveness in enhancing MLLM capabilities. The project page is at https://vcu-bridge.github.io .

cs.CV↗

arXiv2026

DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering

Answering complex questions over large document collections requires assembling complementary evidence across sections and documents. GraphRAG offers structured retrieval but typically uses fixed traversal, while agentic RAG operates over weakly structured interfaces. Our key insight is that agents should navigate document structure within and across documents rather than repeatedly search from scratch. We introduce DocNavRAG, which organizes document hierarchies and cross-region relations into a navigable graph, exposes graph operations for locating, navigating, expanding, and fetching, and maintains an evolving evidence state to guide retrieval until sufficient evidence is collected. Across four long- and multi-document QA benchmarks, DocNavRAG improves answer quality and context sufficiency over the strongest baseline by 7.8\% and 17.7\% on average.

cs.CL↗

arXiv2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

cs.AI↗

arXiv2026

Event-Structured Physics-Informed Neural Networks for Differentiable Critical Clearing Boundaries

Transient-stability assessment determines whether a power system can recover after a disturbance and is therefore essential to preventing generator trips and cascading outages. A key metric is the critical clearing time (CCT), which specifies the maximum time available to clear a fault before synchronism is lost. Reliable CCT estimation is challenging because complicated fault-clearing dynamics require repeated simulations over many fault severities and clearing times. We propose an event-structured physics-informed neural network (ES-PINN) that aligns its representation with the pre-fault, fault-on, and post-clearing swing dynamics and enforces exact state chaining across event interfaces. A smooth trajectory-induced stability margin defines a differentiable approximation of the CCT boundary, enabling accurate boundary extraction, local sensitivity analysis, and optional direct CCT prediction through a distilled readout. We further prove a local residual-to-trajectory-to-CCT error estimate, in which exact event chaining eliminates separate state-interface defect terms. Experiments on IEEE 9-, 14-, and 30-bus systems show that ES-PINN consistently improves held-out trajectory and stability-boundary accuracy over matched neural-surrogate baselines across mechanical and electrical contingencies with multiple clearing configurations. Additional full-network DAE validation, multi-fault experiments, and runtime analyses further demonstrate the effectiveness and computational efficiency of the proposed framework.

cs.LG↗

arXiv2026

How Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought Trajectories

Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpretability methods rely on output-level signals or collapse processing depth into a single trajectory-level scalar, leaving step-wise effort opaque. We propose Step-Aware Reasoning Energy (SARE), a geometric framework that quantifies effort at the granularity of individual CoT steps via Centered Kernel Alignment (CKA) between Gram matrices of token hidden states across adjacent transformer layers, capturing inter-token relational structure without requiring eigenvector alignment or cluster correspondence. SARE further contextualizes this energy within reasoning's semantic progression by modeling CoT trajectories as transitions among latent semantic states. Across six reasoning benchmarks and three open-weight LLMs, we find that reasoning energy is highly non-uniform across step types, exhibiting phase-like transitions invisible to trajectory-level metrics; incorrect trajectories show systematically lower energy at critical reasoning junctions; and SARE-based features match or outperform output-based confidence baselines in most settings, indicating that internal geometric dynamics encode predictive information beyond surface-level signals.

cs.AI↗

arXiv2026

QuTuner: Feature- and Learning-Guided Optimization Pass Tuning for Quantum Compilers

Quantum compilers play a key role in transforming quantum circuits into lower-cost implementations with improved execution fidelity. This process is commonly guided by circuit-level metrics, such as gate counts and circuit depth. Although compiler pass tuning has been widely studied in classical compilation, directly transferring these techniques to quantum compilers is challenging, because quantum programs are expressed as circuits and exhibit optimization behaviors that are shaped by quantum-specific structures. Prior quantum compiler tuning approaches have begun to use circuit features to guide pass selection, but they remain limited in two aspects: they search only a small portion of the optimization-pass space, and they mainly rely on static features that do not explicitly reflect how a circuit reacts to compiler optimizations. We present QuTuner, a feature-guided quantum compiler pass tuning framework that generalizes across compilers and tuning objectives. QuTuner first builds a large optimization dataset. It then characterizes each circuit from two complementary views: static circuit features that describe circuit structure, and optimization-aware pass embeddings that summarize the circuit's responses to individual optimization passes. Using these representations, QuTuner trains two offline models to retrieve and rank candidate pass sequences for unseen circuits, followed by lightweight refinement. We evaluate QuTuner on Qiskit and PyTKET using two benchmark suites. On Qiskit, QuTuner improves the evaluation-metric reduction by up to 84.85% over the strongest baseline while reducing tuning time by 73.59%. On PyTKET, it improves metric reduction by up to 18.68% with a 64.49% reduction in tuning time. These results show that QuTuner provides an effective approach to adaptive pass tuning for quantum compilers.

quant-ph↗

arXiv2026

Lazy-Move Compilation for Neutral-Atom Quantum Computers via a Buffer-Relay Fabric

Neutral atom quantum computing offers strong scalability and flexible qubit connectivity, but most existing compilation flows rely on reconfigurable atom arrays that physically shuttle qubit atoms during execution. Although this approach improves connectivity, it also introduces handoff errors, motional heating, and atom-loss risks that can degrade overall fidelity. We present BRIDGE, a Buffer-Relay Interconnect for Data-stable Gate Execution that co-designs a static, compiler-managed buffer-relay fabric with a lazy-move compiler that exploits it. BRIDGE targets an optimized, dual-species 2D interleaved atom array, using non-encoding ``buffer atoms'' to mediate long-range interactions in the fixed baseline and introducing limited data motion only for selected hotspots. By using calibrated heteronuclear and homonuclear Rydberg channels, BRIDGE realizes a static routing backbone in which data-buffer and buffer-buffer interactions are enabled while residual data-data crosstalk is suppressed. Across a 22-circuit matched benchmark suite re-estimated under a single shared error model, BRIDGE attains a geometric-mean $\sim$10$\times$ higher total fidelity than ZAP and $\sim$16$\times$ than Enola, together with $\sim$540$\times$ and $\sim$1000$\times$ lower circuit execution time, respectively, while reducing data-atom movement from thousands of transport events to zero.

quant-ph↗

arXiv2026

Querying Cohesive Subgraph regarding Span-Constrained Triangles on Temporal Graphs with Dynamic Index Maintenance

Recent advances in temporal graph research have redefined traditional static graph concepts such as triangles, motifs, and $k$-cores. Inspired by this, we introduce a novel $(k,δ)$-truss for temporal graphs, requiring triangles to exist within sufficiently short time windows. The $(k,δ)$-truss ensures both static and temporal cohesion, while the original $k$-truss is a special case when $δ= \infty$. To address $(k,δ)$-truss queries, we propose index-free and index-based approaches. Utilizing the dual containment relation of $(k,δ)$-trusses, our indexes losslessly compress all $(k,δ)$-trusses into map or tree structures, significantly reducing space while enabling optimal-time retrieval. To scale to large temporal graphs, we develop two index construction algorithms based on truss decomposition and truss maintenance, respectively, which substantially reduce redundant computations. Moreover, we present techniques for the dynamic maintenance of the proposed indexes. The experimental results demonstrate that index-based approaches process queries in interactive time and outperform the index-free approach by 2$\sim$4 orders of magnitude, while the indexes achieve compression ratios of up to $10^{-4}$ and can be updated efficiently without rebuilding from scratch.

cs.DB↗

arXiv2026

SWE-IF: Aligning Code Evaluation with Human Preference

Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their vibe check. Vibe check reflects human preference and goes beyond functionality: the solution should feel right, read cleanly, preserve intent, and remain correct. However, current code evaluation remains anchored to pass@k and captures only functional correctness, overlooking non-functional instructions that users routinely apply. In this paper, we hypothesize that instruction following is the missing piece underlying vibe check besides functional correctness. To quantify models' code instruction-following capabilities with measurable signals, we present VeriCode, a taxonomy of 30 verifiable code instructions together with deterministic verifiers. We use the taxonomy to augment established evaluation suites, resulting in SWE-IF, a testbed to assess both instruction following and functional correctness. Evaluating 31 LLMs, we show that even the strongest models struggle to comply with multiple instructions and exhibit functional regression. Most importantly, a composite score of functional correctness and instruction following correlates best with human preference, with instruction following emerging as the primary differentiator among LLMs. Our code, data, and taxonomy are available at https://github.com/maszhongming/SWE-IF.

cs.CL↗