arXiv subjects

Xiang Gu

Publications and source records attributed to Xiang Gu.

At least 19 recordsLinked to original sources

arXiv2026

State-Space Model-Enabled Reinforcement Learning for Magnetic Configuration Controlon EXL-50U

Accurate feedback control of the plasma current ($I_p$) and centroid position $(R_c,Z_c)$ is essential for the stable operation of spherical torus (ST) plasmas. Conventional proportional-integral-derivative (PID) controllers require extensive manual tuning and struggle with the fast, strongly coupled dynamics that arise as plasma performance improves. Reinforcement learning (RL) has recently emerged as a promising alternative to such complex magnetic control problems, yet its practical deployment on ST devices remains challenging. This paper presents a practical RL controller for the EXL-50U ST, trained within a rigid RZIP state-space model (SSM) that enables efficient offline policy learning. A lightweight plasma position reconstructor is developed to estimate $(R_c,Z_c)$ from magnetic probe signals within the real-time control cycle. The trained policy is seamlessly deployed on the EXL-50U plasma control system, achieving stable regulation of $I_p$ and $(R_c,Z_c)$ and sustaining discharges up to 650 ms under RL control. These results demonstrate the feasibility and practical potential of model-informed RL for magnetic configuration control in ST devices, offering a promising direction beyond conventional PID-based schemes.

physics.plasm-ph↗

arXiv2026

Advantage-level Aggregation Reinforcement Learning for X-point Target Magnetic Configuration Control in an EXL-50U Experiment-Calibrated Simulation Environment

Managing divertor heat loads is a central challenge for compact, high-power tokamaks. To increase local flux expansion and decouple the dissipation volume from the core, EHL-2 adopts the X-point target (XPT) divertor. This requires the secondary X-point to remain on the divertor leg; displacement degrades the topology and exhaust geometry. Current experiments, including EXL-50U discharges, rely on precomputed feedforward waveforms with PID loops on global quantities. Lacking dedicated closed-loop feedback for the secondary null, XPT operation is repeatable but not routine. We formulate XPT feedback as a multi-objective reinforcement learning (RL) control problem in a free-boundary environment calibrated to EXL-50U discharge #13906. To address strong coupling among plasma current, shape, and null constraints - where reward scalarisation collapses objective-specific temporal credit - we develop Advantage Aggregation (AdvA). AdvA preserves objective-wise temporal credit before worst-objective-aware nonlinear scalarisation and introduces a residual correction to policy updates. AdvA-PPO is evaluated against Reward-PPO and a feedforward-plus-PID baseline under nominal operation, measurement uncertainties, and unseen initial equilibria. On a 500 ms rollout, AdvA-PPO raises the mean worst-channel score from 0.23 to 0.81 over Reward-PPO, reducing X-point flux RMSE by ~20x. Under combined measurement uncertainties, it is the only learned controller completing the horizon while retaining a usable XPT shape. Multi-initialization fine-tuning enables a single AdvA-PPO policy to complete full-horizon operation across divertor and limiter initial equilibria. These results provide a simulation-based foundation for future real-time XPT validation on EXL-50U.

physics.plasm-ph↗

arXiv2026

Reinforcement learning for vertical position control on the EXL-50U spherical tokamak

Vertical position control is essential for sustaining high-performance operation in spherical tokamaks, where increased plasma elongation introduces stringent requirements on fast and robust stabilization. This work presents an experimentally validated reinforcement-learning(RL)-based vertical position control framework for the EXL-50U spherical tokamak. A high-fidelity discharge-reconstructed simulation environment is developed by integrating physics-based plasma-circuit models with experimental equilibrium information, enabling systematic controller synthesis and sim-to-real evaluation. Within this framework, RL is benchmarked in simulation against operational proportional--integral--derivative (PID) and model-based linear quadratic regulator (LQR) controllers under identical plant dynamics, actuator constraints, and measurement imperfections.Simulation results show that RL achieves tracking accuracy comparable to PID with consistently lower vertical-stabilization coil effort, while lightweight integral compensation improves robustness against residual model--plant mismatch. The RL controller is subsequently deployed on EXL-50U for closed-loop experiments. Across more than ten discharges with RL takeover, stable vertical regulation is achieved within the controlled windows. For seven representative discharges, RL maintains millimetre-scale tracking accuracy comparable to the operational PID controller (MAE typically ~ 1-5 mm) while consistently reducing actuator effort. These results demonstrate the feasibility of learning-based plasma control on a real spherical tokamak and establish a practical pathway toward future fusion control systems.

physics.plasm-ph↗

arXiv2026

Coupled Optimal Transport with Landmark Constraints

Existing optimal transport (OT) models primarily seek an OT map or plan between distributions by minimizing a prescribed transport cost or distortion. However, minimizing transport cost or distortion alone may fail to identify a geometrically meaningful transformation between the two distributions. To address this limitation, this paper proposes a novel coupled OT framework that leverages a small number of annotated landmarks to guide the recovery of an underlying deformation governing the distribution transformation. The coupled OT framework integrates the optimization of the transport plan and the deformation field into a unified model, where the landmark-guided deformation field and the cost-driven transport plan are coupled through a mutual-consistency constraint. As a result, the deformation is jointly determined by the annotated landmarks and cost-driven distribution matching. The proposed framework provides a principled connection between landmark-based registration and transport-based distribution matching, enabling the recovery of transport maps from sparse geometric supervision. We establish the well-definedness of the proposed model in a general variational setting and develop a finite-element-based numerical algorithm for computation whose convergence properties are systematically analyzed. The practical effectiveness of the proposed approach is verified in shape matching.

cs.CV↗

arXiv2026

Mode 0: Architecture, Risk Taxonomy, and Standardization Pathway for RCU-Assisted V2X Safety Communication

The 3GPP V2X resource allocation framework offers two entity classes for coordinating vehicle communication --- base-station scheduling and autonomous vehicle selection --- a design space we show to be structurally incomplete for safety-critical coordination. We propose Mode 0, a third entity class centered on the Roadside Computing Unit (RCU): infrastructure integrating elevated sensing, sidelink communication, and local computation, owned by traffic management authorities rather than network operators. We formalize Mode 0's subfamily taxonomy (Mode 0a through 0c), its traffic risk taxonomy and mandatory-escalation boundary, its cross-domain coexistence with Modes 1-4, and its standardization pathway. Of the three failure modes motivating this proposal --- scheduling saturation, occlusion-driven information gaps, and an institutional authority gap during severe hazards --- only scheduling is evaluated by simulation; information and authority are argued architecturally and evidenced by independent deployment convergence across Chinese national standards, Chinese operator infrastructure, and European and US C-V2X programs, properties no channel-level simulation can meaningfully instantiate. A fifteen-run multi-agent reinforcement learning simulation shows shared-actor policies empirically converge to the analytical coordination floor for independent uniform selection. Pairing per-vehicle actors with demand separation achieves strict Pareto improvement for both traffic classes when the safety pool is correctly sized, and --- in the undersized regime where collision-free assignment is combinatorially impossible --- still lifts worst-TTI delivery reliability (5th-percentile intra-episode M0 packet delivery ratio) from 0.113 to 0.601, the only tested configuration whose delivery protection holds structurally rather than on average. We call for a 3GPP study item to formalize Mode 0.

cs.NI↗

arXiv2026

The DAWN of World-Action Interactive Models

A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action Models (WAMs) largely miss this reciprocity, treating world prediction and action generation as either isolated parallel branches or rigid predict-then-plan pipelines. We formalize this perspective as World-Action Interactive Models (WAIMs), and instantiate it in autonomous driving with \textbf{DAWN} (\textbf{D}enoising \textbf{A}ctions and \textbf{W}orld i\textbf{N}teractive model), a simple yet strong latent generative baseline. DAWN operates in a compact semantic latent space and couples a \emph{World Predictor} with a \emph{World-Conditioned Action Denoiser}: the predicted world hypothesis conditions action denoising, while the denoised action hypothesis is fed back to update the world prediction, so that both are recursively refined during inference. Rather than eliminating test-time world evolution altogether or rolling out the full future in pixel space, DAWN performs a short explicit latent rollout that is sufficient to support long-horizon trajectory generation in complex interactive scenes. Experiments show that DAWN achieves strong planning performance and favorable safety-related results across multiple autonomous driving benchmarks. More broadly, our results suggest that interactive world-action generation is a principled path toward truly actionable world models.

cs.CV↗

arXiv2026

A Residual-Shell-Based Lower Bound for Ollivier-Ricci Curvature

Ollivier-Ricci curvature (ORC), defined via the Wasserstein distance that captures rich geometric information, has received growing attention in both theory and applications. However, the high computational cost of Wasserstein distance evaluation has significantly limited the broader practical use of ORC. To alleviate this issue, previous work introduced a computationally efficient lower bound as a proxy for ORC based on 1-hop random walks, but this approach empirically exhibits large gaps from the exact ORC. In this paper, we establish a substantially tighter lower bound for ORC than the existing lower bound, while retaining much lower computational cost than exact ORC computation, with practical speedups of tens of times. Moreover, our bound is not restricted to 1-hop random walks, but also applies to k-hop random walks (k > 1). Experiments on several fundamental graph structures demonstrate the effectiveness of our bound in terms of both approximation accuracy and computational efficiency.

cs.LG↗

arXiv2026

Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration

Despite substantial advances in all-in-one image restoration for addressing diverse degradations within a unified model, existing methods remain vulnerable to out-of-distribution degradations, thereby limiting their generalization in real-world scenarios. To tackle the challenge, this work is motivated by the intuition that multisource degraded feature distributions are induced by different degradation-specific shifts from an underlying degradation-agnostic distribution, and recovering such a shared distribution is thus crucial for achieving generalization across degradations. With this insight, we propose BaryIR, a representation learning framework that aligns multisource degraded features in the Wasserstein barycenter (WB) space, which models a degradation-agnostic distribution by minimizing the average of Wasserstein distances to multisource degraded distributions. We further introduce residual subspaces, whose embeddings are mutually contrasted while remaining orthogonal to the WB embeddings. Consequently, BaryIR explicitly decouples two orthogonal spaces: a WB space that encodes the degradation-agnostic invariant contents shared across degradations, and residual subspaces that adaptively preserve the degradation-specific knowledge. This disentanglement mitigates overfitting to in-distribution degradations and enables adaptive restoration grounded on the degradation-agnostic shared invariance. Extensive experiments demonstrate that BaryIR performs competitively against state-of-the-art all-in-one methods. Notably, BaryIR generalizes well to unseen degradations (\textit{e.g.,} types and levels) and shows remarkable robustness in learning generalized features, even when trained on limited degradation types and evaluated on real-world data with mixed degradations.

cs.CV↗

arXiv2026

CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction

Fully unsupervised deep generative modeling (FU-DGM) offers significant potential for compressively sampled magnetic resonance imaging (CS-MRI) reconstruction. Representative FU-DGM formulations, such as deep image prior (DIP) and implicit neural representation (INR), employ architectural bias to induce a low-dimensional manifold in the image space that aligns with the forward observation. However, as the underlying inverse system is highly ill-posed, prolonged iterative fitting in FU-DGM typically leads to poor efficiency and noise amplification. In this paper, guided by the cognitive principle of easy-to-hard learning, we propose CogGen, an FU-DGM framework that reformulates CS-MRI reconstruction as a staged inversion problem. Specifically, CogGen implements an self-paced curriculum learning (SPCL)-driven progressive scheduling strategy through an MRI-aware dual-threshold weighting criterion, which adaptively regulates k-space measurement participation. The data-consistency residual thresholding evaluates the fitting reliability of the current generator, while the k-space radius thresholding controls stage-wise measurement exposure, thereby avoiding uniform fitting throughout optimization. Theoretically, our analysis shows that, when early stages favor easy-to-fit measurements, CogGen yields a reduced local sufficient-iteration bound and a smaller cumulative noise-amplification bound, explaining the improved convergence behavior and reconstruction fidelity of CogGen within a finite iteration budget. Numerical experiments demonstrate that both CogGen instantiations, CogGen-DIP and CogGen-INR, achieve superior performance over prevailing CS-MRI reconstruction techniques, including unsupervised and supervised pipelines.

eess.IV↗

arXiv2025

Non-Inductive Current Start-Up Using Multi-Harmonic Electron Cyclotron Wave and Current Ramp-Up Through Combined Electron Cyclotron Wave and Ohmic Heating in EXL-50U Spherical Torus

The non-inductive current start-up by multi-harmonic electron cyclotron wave has been systematically investigated in the EXL-50U spherical torus. Significant enhancements of the driven current with increasing number of resonance layers have been demonstrated by variation of the number of harmonic resonance layers of the ECW through adjustment of the magnetic field or plasma cross section. The critical role of multi-harmonic ECW in enhancing the driven current has been experimentally verified for the first time. To explain the related experimental observations, a physical mechanism involving multi-harmonic heating, multiple reflections, and multi-pass absorption - leading to the generation of high-energy electrons via X-mode wave or electron Bernstein wave has been proposed. The current drive capacity of the first harmonic extraordinary mode of the ECW has also been experimentally confirmed for the first time. After the application of Ohmic heating during the current ramp-up phase, the current drive efficiency of ECW is further enhanced. Leveraging the synergistic effect between ECW and Ohmic heating, EXL-50U achieved a plasma current of 1 MA, with the non-inductively driven current fraction reaching 70%.

physics.plasm-ph↗

arXiv2025

DREAM: Dynamic Red-teaming across Environments for AI Models

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static, single-turn assessments that miss vulnerabilities from adaptive, long-chain attacks. To fill this gap, we introduce DREAM, a framework for systematic evaluation of LLM agents against dynamic, multi-stage attacks. At its core, DREAM uses a Cross-Environment Adversarial Knowledge Graph (CE-AKG) to maintain stateful, cross-domain understanding of vulnerabilities. This graph guides a Contextualized Guided Policy Search (C-GPS) algorithm that dynamically constructs attack chains from a knowledge base of 1,986 atomic actions across 349 distinct digital environments. Our evaluation of 12 leading LLM agents reveals a critical vulnerability: these attack chains succeed in over 70% of cases for most models, showing the power of stateful, cross-environment exploits. Through analysis of these failures, we identify two key weaknesses in current agents: contextual fragility, where safety behaviors fail to transfer across environments, and an inability to track long-term malicious intent. Our findings also show that traditional safety measures, such as initial defense prompts, are largely ineffective against attacks that build context over multiple interactions. To advance agent safety research, we release DREAM as a tool for evaluating vulnerabilities and developing more robust defenses.

cs.CR↗

arXiv2025

Multimodal Robust Prompt Distillation for 3D Point Cloud Models

Adversarial attacks pose a significant threat to learning-based 3D point cloud models, critically undermining their reliability in security-sensitive applications. Existing defense methods often suffer from (1) high computational overhead and (2) poor generalization ability across diverse attack types. To bridge these gaps, we propose a novel yet efficient teacher-student framework, namely Multimodal Robust Prompt Distillation (MRPD) for distilling robust 3D point cloud model. It learns lightweight prompts by aligning student point cloud model's features with robust embeddings from three distinct teachers: a vision model processing depth projections, a high-performance 3D model, and a text encoder. To ensure a reliable knowledge transfer, this distillation is guided by a confidence-gated mechanism which dynamically balances the contribution of all input modalities. Notably, since the distillation is all during the training stage, there is no additional computational cost at inference. Extensive experiments demonstrate that MRPD substantially outperforms state-of-the-art defense methods against a wide range of white-box and black-box attacks, while even achieving better performance on clean data. Our work presents a new, practical paradigm for building robust 3D vision systems by efficiently harnessing multimodal knowledge.

cs.CV↗

arXiv2025

Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov Equation

As artificial intelligence emerges as a transformative enabler for fusion energy commercialization, fast and accurate solvers become increasingly critical. In magnetic confinement nuclear fusion, rapid and accurate solution of the Grad-Shafranov equation (GSE) is essential for real-time plasma control and analysis. Traditional numerical solvers achieve high precision but are computationally prohibitive, while data-driven surrogates infer quickly but fail to enforce physical laws and generalize poorly beyond training distributions. To address this challenge, we present a Physics-Informed Neural Operator (PINO) that directly learns the GSE solution operator, mapping shape parameters of last closed flux surface to equilibrium solutions for realistic nonlinear current profiles. Comprehensive benchmarking of five neural architectures identifies the novel Transformer-KAN (Kolmogorov-Arnold Network) Neural Operator (TKNO) as achieving highest accuracy (0.25% mean L2 relative error) under supervised training (only data-driven). However, all data-driven models exhibit large physics residuals, indicating poor physical consistency. Our unsupervised training can reduce the residuals by nearly four orders of magnitude through embedding physics-based loss terms without labeled data. Critically, semi-supervised learning--integrating sparse labeled data (100 interior points) with physics constraints--achieves optimal balance: 0.48% interpolation error and the most robust extrapolation performance (4.76% error, 8.9x degradation factor vs 39.8x for supervised models). Accelerated by TensorRT optimization, our models enable millisecond-level inference, establishing PINO as a promising pathway for next-generation fusion control systems.

physics.plasm-ph↗

arXiv2025

Generating transition states of chemical reactions via distance-geometry-based flow matching

Transition states (TSs) are crucial for understanding reaction mechanisms, yet their exploration is limited by the complexity of experimental and computational approaches. Here we propose TS-DFM, a flow matching framework that predicts TSs from reactants and products. By operating in molecular distance geometry space, TS-DFM explicitly captures the dynamic changes of interatomic distances in chemical reactions. A network structure named TSDVNet is designed to learn the velocity field for generating TS geometries accurately. On the benchmark dataset Transition1X, TS-DFM outperforms the previous state-of-the-art method React-OT by 30\% in structural accuracy. These predicted TSs provide high-quality initial structures, accelerating the convergence of CI-NEB optimization. Additionally, TS-DFM can identify alternative reaction paths. In our experiments, even a more favorable TS with lower energy barrier is discovered. Further tests on RGD1 dataset confirm its strong generalization ability on unseen molecules and reaction types, highlighting its potential for facilitating reaction exploration.

cs.LG↗

arXiv2025

CIARD: Cyclic Iterative Adversarial Robustness Distillation

Adversarial robustness distillation (ARD) aims to transfer both performance and robustness from teacher model to lightweight student model, enabling resilient performance on resource-constrained scenarios. Though existing ARD approaches enhance student model's robustness, the inevitable by-product leads to the degraded performance on clean examples. We summarize the causes of this problem inherent in existing methods with dual-teacher framework as: 1. The divergent optimization objectives of dual-teacher models, i.e., the clean and robust teachers, impede effective knowledge transfer to the student model, and 2. The iteratively generated adversarial examples during training lead to performance deterioration of the robust teacher model. To address these challenges, we propose a novel Cyclic Iterative ARD (CIARD) method with two key innovations: a. A multi-teacher framework with contrastive push-loss alignment to resolve conflicts in dual-teacher optimization objectives, and b. Continuous adversarial retraining to maintain dynamic teacher robustness against performance degradation from the varying adversarial examples. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that CIARD achieves remarkable performance with an average 3.53 improvement in adversarial defense rates across various attack scenarios and a 5.87 increase in clean sample accuracy, establishing a new benchmark for balancing model robustness and generalization. Our code is available at https://github.com/eminentgu/CIARD

cs.CV↗

arXiv2025

BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image Restoration

Despite remarkable advances made in all-in-one image restoration (AIR) for handling different types of degradations simultaneously, existing methods remain vulnerable to out-of-distribution degradations and images, limiting their real-world applicability. In this paper, we propose a multi-source representation learning framework BaryIR, which decomposes the latent space of multi-source degraded images into a continuous barycenter space for unified feature encoding and source-specific subspaces for specific semantic encoding. Specifically, we seek the multi-source unified representation by introducing a multi-source latent optimal transport barycenter problem, in which a continuous barycenter map is learned to transport the latent representations to the barycenter space. The transport cost is designed such that the representations from source-specific subspaces are contrasted with each other while maintaining orthogonality to those from the barycenter space. This enables BaryIR to learn compact representations with unified degradation-agnostic information from the barycenter space, as well as degradation-specific semantics from source-specific subspaces, capturing the inherent geometry of multi-source data manifold for generalizable AIR. Extensive experiments demonstrate that BaryIR achieves competitive performance compared to state-of-the-art all-in-one methods. Particularly, BaryIR exhibits superior generalization ability to real-world data and unseen degradations. The code will be publicly available at https://github.com/xl-tang3/BaryIR.

cs.CV↗

arXiv2025

Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport

Medical image reconstruction from measurement data is a vital but challenging inverse problem. Deep learning approaches have achieved promising results, but often requires paired measurement and high-quality images, which is typically simulated through a forward model, i.e., retrospective reconstruction. However, training on simulated pairs commonly leads to performance degradation on real prospective data due to the retrospective-to-prospective gap caused by incomplete imaging knowledge in simulation. To address this challenge, this paper introduces imaging Knowledge-Informed Dynamic Optimal Transport (KIDOT), a novel dynamic optimal transport framework with optimality in the sense of preserving consistency with imaging physics in transport, that conceptualizes reconstruction as finding a dynamic transport path. KIDOT learns from unpaired data by modeling reconstruction as a continuous evolution path from measurements to images, guided by an imaging knowledge-informed cost function and transport equation. This dynamic and knowledge-aware approach enhances robustness and better leverages unpaired data while respecting acquisition physics. Theoretically, we demonstrate that KIDOT naturally generalizes dynamic optimal transport, ensuring its mathematical rationale and solution existence. Extensive experiments on MRI and CT reconstruction demonstrate KIDOT's superior performance.

eess.IV↗

arXiv2025

Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling

Learning the underlying dynamics of single cells from snapshot data has gained increasing attention in scientific and machine learning research. The destructive measurement technique and cell proliferation/death result in unpaired and unbalanced data between snapshots, making the learning of the underlying dynamics challenging. In this paper, we propose joint Velocity-Growth Flow Matching (VGFM), a novel paradigm that jointly learns state transition and mass growth of single-cell populations via flow matching. VGFM builds an ideal single-cell dynamics containing velocity of state and growth of mass, driven by a presented two-period dynamic understanding of the static semi-relaxed optimal transport, a mathematical tool that seeks the coupling between unpaired and unbalanced data. To enable practical usage, we approximate the ideal dynamics using neural networks, forming our joint velocity and growth matching framework. A distribution fitting loss is also employed in VGFM to further improve the fitting performance for snapshot data. Extensive experimental results on both synthetic and real datasets demonstrate that VGFM can capture the underlying biological dynamics accounting for mass and state variations over time, outperforming existing approaches for single-cell dynamics modeling.

cs.LG↗