Search arXiv⌕ Search

arXiv subjects

Qiang Chen

Publications and source records attributed to Qiang Chen.

At least 19 recordsLinked to original sources
arXiv2026

Dual-Frontier: When Can an Agent Trust Its World Model?

Learned world models are becoming essential to general-purpose agents: by predicting action consequences, they support planning and decision-making while reducing reliance on costly trial and error. This reliance creates a fundamental ambiguity: when a world-model-guided decision fails, the trajectory alone may not reveal whether the agent's decision rule or the world model caused the loss. We formalize this failure-attribution problem as a counterfactual decomposition of return loss and prove that its components are not identifiable from passive interaction, even for finite-horizon planners. This obstruction motivates Dual-Frontier, a learning principle that admits a world-model-guided decision only when its predicted advantage exceeds a certified bound on decision-relevant world-model error; otherwise, evidence is allocated to world-model verification. Action-conditioned value bounds and a closed-loop extension guarantee non-decreasing return for admitted decisions. Calibrated gates and simultaneous confidence sequences support adaptive evidence reuse, with sufficient and necessary verification bounds. Controlled learned-model experiments validate the predicted failure modes and certification behavior, while cross-backbone tool-use benchmarks instantiate the same verify-then-promote rule in realistic agent world-model pipelines, consistently improving decision quality and reliability.

cs.AI↗
arXiv2026

FireWorldBench: Benchmarking Complex Physical World Intelligence through Coupled-Field Fire Dynamics

Understanding the physical world requires more than object recognition, scene description, and short-term visual prediction, as real-world physical systems involve multiple continuous fields, latent causal mechanisms, partial observations, and intervention-sensitive dynamics. We propose FireWorldBench, a benchmark for evaluating complex physical world intelligence in multimodal large language models and agents through coupled-field fire dynamics. Fire provides a canonical stress-test environment, where multiple interacting physical fields jointly shape observable states and temporal dynamics. FireWorldBench is organized along two complementary axes, a physical capability axis and a fire scenario task axis, jointly covering physical-state understanding, temporal dynamics, causal mechanisms, and intervention reasoning. The benchmark comprises 520 fire-world entries, including 494 controlled simulation worlds and 26 real-world-aligned event groups, spanning 47 scene archetypes across 7 environment families. These entries combine structured textual observations, multiple 2D physical-field visualizations, and 3D event-level scene modeling, yielding 9,074 text-image interleaved question-answer pairs across choice-based and open-ended report-generation formats. FireWorldBench evaluates whether models can infer latent physical states, explain underlying mechanisms, forecast coupled-field evolution, and assess intervention consequences from multimodal partial observations, providing a challenging testbed for complex physical world intelligence.

cs.AI↗
arXiv2026

A HIP-Compatible Accelerator Backend for Fourier-Bessel Particle-in-Cell Simulations on CPU/DCU Heterogeneous Clusters

FBPIC (Fourier-Bessel particle-in-cell) is a high-performance simulation code for relativistic plasma and accelerator physics. Its original accelerator backend relies on Numba CUDA, which limits its direct deployment on accelerators using the HIP (Heterogeneous-Compute Interface for Portability) programming environment, such as DCU (Deep Computing Unit) accelerators. In this work, we develop an accelerator backend compatible with HIP that enables FBPIC to run efficiently on DCU platforms while preserving its Python user interface and high level simulation workflow. For the evaluated LWFA (laser-wakefield acceleration) workloads, the proposed backend achieves 1.32-1.54x speedups over the original FBPIC implementation on an NVIDIA V100 GPU and enables efficient execution on the DCU platform. We also summarize the key lessons learned from porting FBPIC to the DCU platform. Multi-DCU experiments achieve a 1.88x strong-scaling speedup on four accelerators and a 2.72x increase in aggregate throughput at approximately 68\% weak-scaling efficiency, with communication analysis identifying inter-node communication and synchronization as the main scalability limitations. Beyond FBPIC, the proposed approach provides a practical reference for porting and optimizing other scientific computing applications developed with Python on heterogeneous accelerator platforms.

physics.comp-ph↗
arXiv2026

XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment

Robot policy evaluation and deployment remain fragmented by model-specific software dependencies, data representations, and runtime interfaces, so that connecting N policies to M evaluation environments requires O(NM) separate integrations. We present XPolicyLab, a unified standard and open ecosystem that reduces this cost to O(N+M). XPolicyLab specifies common observation, action, and trajectory schemas together with a minimal adapter interface for observation updates, action prediction, batched execution, and episode reset, while a dependency-isolated client/server architecture separates policy inference from environment execution, so that each side retains its native software stack and may run locally or remotely. The ecosystem integrates 42 robot policies and standardizes their installation, debugging, serving, and evaluation workflows. Across these adapters, model-specific code varies by an order of magnitude while the environment-facing loop stays within a few lines of a fixed reference, confirming that the contract confines heterogeneity to the policy side. In a controlled study, conforming to the standard reduces the integration effort of a representative policy from over five hours to two hours, and packaged agent skills reduce it further to thirty minutes. The same adapters serve RoboTwin, RoboDojo simulation, and standardized real-robot evaluation through one interface. XPolicyLab is released as shared infrastructure for reproducible policy comparison and standardized deployment across simulation and physical platforms. Project website: https://xpolicylab.github.io/.

cs.RO↗
arXiv2026

Tools as Continuous Flow for Evolving Agentic Reasoning

Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a step-wise paradigm that lacks a global perspective, which causes error accumulation over long horizons and restricts generalization to unseen tools. To overcome these limitations, we propose Tools as Continuous Flow for Evolving Agentic Reasoning (FlowAgent), which reconceptualizes tool chaining as continuous trajectory generation within a semantic space. To systematically evaluate this paradigm, we introduce the first plan-level closed-loop benchmark dedicated to plan-level agentic reasoning in dynamic real-world environments. Specifically, the proposed FlowAgent leverages conditional flow matching to generate continuous latent trajectories, providing a global planning perspective to ensure coherent and robust tool execution. Theoretically, we establish formal bounds on utility convergence and prove that our continuous formulation fundamentally guarantees robust generalization and error attenuation. Empirical evaluations show that FlowAgent achieves superior robustness and adaptability in long-horizon reasoning tasks.

cs.AI↗
arXiv2026

DriveVLA-M0: Failure-Aware Memory Augmentation for Autonomous Driving

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for end-to-end autonomous driving by enabling unified reasoning across perception, language, and planning. However, existing approaches lack mechanisms to exploit past failures or adapt to distribution shifts, causing the model to persistently underperform on similar scenarios where it has previously failed. In this paper, we propose DriveVLA-M0, a retrieval-augmented VLA with failure-aware latent memory. We construct a latent memory pool that stores failure cases along with their structure scene representations and expert trajectory labels, and design a dedicated Retrieve Model that decouples static road structure and dynamic agent interactions to enable structurally grounded retrieval. At inference time, retrieved cases are injected into the model via a lightweight decoupled LoRA-based test-time training (TTT) mechanism, allowing targeted and scenario-specific correction without modifying the backbone. Extensive experiments on NAVSIMv1 and NAVSIMv2 benchmark demonstrate that our approach consistently outperforms prior methods, achieving 94.1 PDMS on Navtest and 47.0 EPDMS on Navhard with only 26.44 ms TTT backward latency overhead. Furthermore, we show that DriveVLA-M0 scales effectively with additional memory, enabling training-free performance gains through memory expansion. The code is available at https://github.com/ZebinX/DriveVLA-M0.

cs.CV↗
arXiv2026

FusionMMT: A Unified Multimodal and Multitask Learning Framework for Nuclear Fusion

With the growing global demand for energy, nuclear fusion has emerged as a promising direction for future clean energy. Tokamaks represent one of the leading approaches to magnetic-confinement fusion. Achieving high-performance, long-pulse, and steady-state operation requires effective diagnosis of plasma states. However, existing intelligent diagnostic methods are largely limited to either multimodal single-task or unimodal multitask learning, while a unified multimodal multitask learning framework remains underexplored. To address this gap, we construct EAST-VTD640, a multimodal multitask dataset that integrates vision and time-series diagnostics from 640 EAST shots for disruption prediction, edge-localized mode (ELM) recognition, and H98 regression. On this basis, we present FusionMMT, the first unified multimodal multitask framework for intelligent tokamak plasma diagnostics. FusionMMT employs multi-scale, time-aware, and variable-aware modeling to handle heterogeneous sampling rates and the high computational cost of high-frequency sequences. It further combines task-adaptive multimodal fusion with progressive multitask optimization to learn shared and task-specific representations while mitigating cross-task conflicts and optimization imbalance. Extensive experiments on EAST-VTD640 show that FusionMMT outperforms representative multimodal multitask methods across disruption prediction, ELM recognition, and H98 regression. The source code will be released on https://github.com/Event-AHU/OpenFusion

cs.AI↗
arXiv2026

A CPU+DCU Heterogeneous Parallel Framework for Post-Processing Reconstruction in Quantum Circuit Cutting

In the NISQ era, limited qubit resources make it difficult to execute large quantum circuits directly on real hardware. Quantum circuit cutting mitigates this limitation by decomposing a large circuit into smaller subcircuits, but it shifts substantial overhead to classical post-processing. As circuit size, complexity, and cut count increase, reconstruction becomes a major computational and storage bottleneck. This paper presents a CPU+DCU heterogeneous parallel framework for circuit-cutting post-processing reconstruction. Instead of constructing a dense $2^n$-dimensional probability vector or returning only high-probability states, the framework reconstructs the nonzero-probability states in the original output distribution from subcircuit measurement results. It combines heterogeneous CPU+DCU execution with a high/low-word integer representation for global basis-state indices beyond 64 bits and a three-level cooperative storage mechanism spanning device memory, host memory, and out-of-core storage. Experiments on the Songshan supercomputer show that the framework maintains high reconstruction fidelity while achieving up to $259\times$ speedup over an optimized serial baseline on linear-cluster states and up to $4\times$ speedup over a homogeneous CPU-parallel method on random circuits. The framework can also complete reconstruction tasks at the hundred-qubit scale. These results demonstrate that HPC-oriented heterogeneous reconstruction can effectively alleviate the classical post-processing bottleneck and improve reconstruction scalability.

quant-ph↗
arXiv2026

Central Equations and Band Structures of Linear Magnetohydrodynamic Waves in a Magneto-Lattice

We investigate the band structures and propagation properties of linear ideal magnetohydrodynamic (MHD) waves in a plasma with a spatially periodic background magnetic field (a magneto-lattice ). We develop a plane-wave expansion approach in two equivalent forms: one written using the usual linearized MHD perturbation variables and another written in terms of the fluid displacement. We validate both formulations with numerical tests, including an empty-lattice limit that recovers the uniform-plasma dispersion. The method enables efficient computation of dispersion relations and reveals intrinsic frequency band gaps and cutoff behavior caused by magnetic periodicity. We show that the band gap width increases with the amplitude of the periodic magnetic-field modulation (relative to the uniform background field), leading to suppression of selected wave modes. In addition, the magnetic periodicity splits the Alfvén continuum into multiple branches, a feature absent in uniform plasmas. These results provide a framework for tailoring MHD wave propagation in structured plasmas and may be useful for future studies of plasma metamaterials and topological plasma waves.

physics.plasm-ph↗
arXiv2026

ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning

Reinforcement Learning (RL) training for Large Language Models (LLMs) often suffers from instability due to the discrepancy between training and inference. This training-inference discrepancy stems from two primary factors: an architectural separation between training and inference engines, and the use of low-precision quantization in inference versus higher-precision computation in training. To address training instability issues caused by high training-inference discrepancy, we present the principles and methods for its adaptive control. We propose Adaptive Control Reinforcement Learning (ACRL), which adaptively maintains the training-inference discrepancy within a reasonable range to ensure stable RL training. Beyond stabilization, ACRL inherently increases policy entropy, thereby enhancing exploration and improving accuracy. The experimental results show that when the inference engine utilizes FP8 quantization, ACRL consistently maintains the training-inference discrepancy within a reasonable range and stabilizes RL training. Furthermore, ACRL not only matches the accuracy of the BF16 baseline but also outperforms importance sampling (IS) fixes.

cs.LG↗
arXiv2026

The origin of ferroelectricity, polarization and high resistivity in Aurivillius CaBi2B2O9 (B = Ta, Nb)

Aurivillius layered oxides are important candidates for high-temperature ferroelectric and piezoelectric application. In this work, we combine group theoretic analysis with first-principles calculations to systematically investigate the origin of ferroelectric phase transition, polarization, piezoelectric response, and intrinsic electrical insulation of the two-layer Aurivillius ferroelectrics CaBi$_{2}$B$_{2}$O$_{9}$ (B = Ta, Nb). The results show that the \textit{A2$_1$am} ferroelectric phase arises from the cooperative condensation of a polar mode and nonpolar oxygen octahedral rotation/tilting modes, whose the $Γ_5^-$X$_2^+$X$_3^-$ trilinear coupling substantially lowers the total energy and deepens the ferroelectric potential well. The spontaneous polarization and anisotropic piezoelectric response are governed primarily by the cooperative displacements of the Bi$_{2}$O$_{2}$ layers and Ta/NbO$_{6}$ octahedra, with Bi ions providing an indispensable contribution to both responses. More importantly, the polar distortion can be traced to the relative in-plane displacement between adjacent the Bi$_{2}$O$_{2}$ layer and the perovskite-like block. Because this displacement is intrinsic to the alternating Bi$_{2}$O$_{2}$/perovskite-block stacking topology and is independent of the number of perovskite layers, we identify interlayer sliding as a general, layer-number-independent structural mechanism for ferroelectricity in Aurivillius oxides. Our findings establish a unified microscopic picture linking structural distortions, ferroelectric polarization, piezoelectric response, and electronic insulation in CaBi$_{2}$B$_{2}$O$_{9}$ (B = Ta, Nb), and provide theoretical guidance for designing layered ferroelectric oxides with high Curie temperatures and robust insulating behavior.

cond-mat.mtrl-sci↗
arXiv2026

Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model

Nuclear fusion has made significant progress in recent years and is expected to become one of the most important pathways to addressing global energy challenges. This paper focuses on observing plasma using visible-light cameras, analyzing its spatio-temporal motion cues, and predicting the two-dimensional spatial distribution of light intensity, aiming to provide a foundational basis for future scientific experiments using deep neural networks. Specifically, we propose Delta-InvFormer, a novel backbone network centered on a differential Transformer. The key insight is that by taking consecutive video frames as input, we can better capture the dynamics of the plasma. Moreover, spatial and temporal differential self-attention effectively mitigates interference from noisy signals, ensuring high-quality feature extraction. These features are then fused into a compact and informative representation, which is fed into a decoder network to predict the distribution. Based on real experimental data collected from the Experimental Advanced Superconducting Tokamak (EAST) large-scale scientific facility, our results demonstrate that the proposed model not only significantly accelerates traditional methods for distribution prediction but also achieves competitive reconstruction accuracy. The source code of this paper will be released on https://github.com/Event-AHU/OpenFusion

cs.CV↗
arXiv2026

VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation

Recent video generation models (VGMs) have made substantial progress in visual fidelity, yet their ability to follow long, compositional instructions remains insufficiently evaluated. Existing evaluation protocols often rely on prompts that are short and semantically shallow, with limited atomic constraints and weak spatio-temporal dependencies. They also frequently depend on costly human evaluation or handcrafted vision pipelines, while providing little diagnostic insight into which instruction constraints succeed or fail. To address this gap, we propose VGIF-Score, a highly automated and interpretable framework for evaluating instruction following in video generation. VGIF-Score consists of two complementary components: an objective completion branch that parses prompts into a Spatio-Temporal Directed Acyclic Graph (ST-DAG) and performs dependency-aware QA with short-circuit diagnostics, and a subjective satisfaction branch that uses instruction-conditioned AutoRubric to assess cinematography, visual purity, motion smoothness, and physics adherence. Together, these components produce a unified score that captures both objective completion and perceptual satisfaction. We instantiate this framework on VGIF-Bench, a benchmark of 223 long, structurally entangled prompts paired with approximately 4.3K fine-grained evaluation items. Experiments on 14 proprietary and open-source VGMs across more than 3K generated videos show that VGIF-Score provides reliable, interpretable, and diagnostically useful evaluation of video generation instruction following. The code will be available at https://github.com/PRIS-CV/VGIF-SCORE.

cs.CV↗
arXiv2026

Hierarchical Multi-to-Single-Modal Knowledge Distillation for Disruption Prediction in EAST

Plasma disruption is a critical threat to tokamak safety. Existing data-driven predictors mainly rely on time-series diagnostic signals, while visible images provide complementary spatial cues including plasma deformation, local brightening, and radiation-structure evolution. Although the image modality improves the model's discriminative capability, it also substantially increases the computational cost during inference. To address this issue, we propose a hierarchical multi-to-single-modal knowledge distillation framework for disruption prediction on a synchronized EAST multimodal dataset. During training, visible images and time-series signals are used to train a multimodal teacher, which learns disruption precursor representations through Transformer-based encoders and a prototype-guided spatiotemporal hypergraph module. During inference, only the time-series student is retained, with multimodal knowledge transferred through graph-structure-level, representation-level, and decision-level distillation. On the 640-discharge EAST dataset, the results demonstrate that the proposed framework can preserve the discriminative advantages of multimodal learning while substantially reducing inference cost, and providing an effective route for efficient disruption prediction in EAST. The source code of this paper will be released on https://github.com/Event-AHU/OpenFusion.

cs.CV↗
arXiv2026

Decision-Weighted Flow Matching for Contextual Stochastic Optimization

Conditional generative models are increasingly used as scenario generators for stochastic optimization, but standard training objectives emphasize uniform distributional fit rather than the downstream decisions induced by generated scenarios. This creates an objective mismatch: errors in statistically common regions may have little effect on decision regret, whereas errors in decision-sensitive regions can substantially change the optimal action. We propose Decision-Weighted Flow Matching (DW-FM), a regret-aligned training framework that preserves the simplicity of standard flow matching while reweighting its velocity-regression objective using decision-sensitive endpoint information. Theoretically, we connect downstream regret to pathwise velocity mismatch through a loss-induced decision discrepancy and an adjoint transport argument, yielding an ideal regret-aligned surrogate and practical endpoint-weighted objectives with regret guarantees. Empirically, we demonstrate the effectiveness of DW-FM on three CVaR-based contextual stochastic optimization benchmarks spanning synthetic portfolio, semi-real financial, and traffic-CVaR tasks, where DW-FM improves downstream regret over standard baselines.

cs.LG↗
arXiv2026

Sparsified Kolmogorov-Arnold Networks for Interpretable Quantum State Tomography

Machine-learning approaches to quantum state tomography can achieve high reconstruction fidelity, but the physical structure used by the trained model often remains implicit. Here we ask whether a sparsified Kolmogorov-Arnold Network (KAN) can be used not only as a regressor, but also as an inspectable reconstruction rule whose internal organization can be checked against known Pauli structure. We study a controlled three-qubit GHZ-family benchmark in which all 63 non-identity Pauli expectation values are used to reconstruct three GHZ-subspace variables: the population imbalance $z$, the real off-diagonal component $c$, and the imaginary off-diagonal component $s$. Under finite-shot sampling and depolarizing noise, external ablation identifies the extended 12-channel GHZ-relevant Pauli set from the 63 measurements, with exact top-12 recovery across the tested shot counts and depolarizing-noise strengths. These support patterns remain stable across multi-seed random-initialization and noise-level analyses, and collapse under random-label controls. The dominant pruned input-hidden-output pathways organize Z-type population observables and X/Y off-diagonal observables in a pattern consistent with the analytic GHZ Pauli grouping, and sparse formula recovery recovers the canonical signed Pauli relations. The contribution of the KAN is therefore pathway-level structural interpretability within a neural reconstruction model, rather than superior sparse regression. Together with negative controls, these probes provide a consistency chain for auditing learned reconstruction rules against known physical structure.

quant-ph↗
arXiv2026

Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets

Many Markov decision processes (MDPs) in operations research have feasible actions that are state dependent and defined implicitly by various operational constraints. These features make it difficult to use standard deep reinforcement learning (DRL) algorithms, whose action interfaces typically assume either a fixed finite action catalog or a simple Euclidean space. Motivated by a Taylor expansion of the optimal action-value function, we propose Bellman--Taylor score decoding, a framework that moves policy learning to a Euclidean score space while enforcing feasibility through an action decoder. The induced latent-score MDP then can be optimized by standard DRL algorithms without differentiating through the decoder. We provide a performance guarantee showing that the optimality gap of this approach decomposes into a structural approximation error and an algorithmic learning error. Lastly, we apply this framework to a queueing network control problem, where the policy essentially learns a state-dependent index-based dispatching rule. Numerical experiments show near-optimal performance in small instances and considerable improvements over benchmarks in larger systems.

cs.AI↗
arXiv2026

ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems

Recent advances have improved the adaptive capabilities of LLM-based multi-agent systems (MAS) through memory-, skill-, and learning-based approaches, yet these approaches remain challenged by noisy trajectories, insufficient modeling of memory-skill relations, and reliance on additional training or high-quality supervision. To address these limitations, we propose ConMem, a relation-aware and training-free framework that enables efficient multi-agent adaptation through cross-experience coordination. Specifically, ConMem distills historical interaction trajectories into structured memory cards to capture reusable strategies and cues, organizing them into a relation-aware memory graph. At runtime, ConMem retrieves cards according to task needs and coordinates them through the card graph to resolve strategy conflicts and recover their dependencies. Combined, these modules yield structured and relation-aware guidance, enabling robust, lightweight adaptation in multi-agent systems without additional training. Extensive experiments across multiple benchmarks and mainstream MAS architectures show consistent gains over existing memory architectures, with improved inference-time efficiency through pruning more than 50% of expanded candidates and reducing planning overhead by over 80%. Our codes are available at https://anonymous.4open.science/r/ConMemCode

cs.AI↗