arXiv subjects

Haoran He

Publications and source records attributed to Haoran He.

At least 19 recordsLinked to original sources

arXiv2026

QMClaw: A Scalable General-purpose Framework for Quantum Measurement and Control

As quantum computing continues to scale, quantum measurement and control (QMC) are increasingly constrained by calibration workflow complexity and by requirements for low-latency execution, robust exception handling, and traceable workflow governance. Existing frameworks for QMC are specialized and task-specific, while language-model-based agents for QMC suffer from excessive latency and cannot satisfy the strict timing and control-density demands of large-scale quantum systems. Here we propose QMClaw, a general, workflow-oriented framework for QMC built, featuring a local-first, tool-governed, robust architecture. At its core is a RuleEngine-centered control layer that processes structured context, performs rule-based state transitions, and generates execution plans for typical calibration workflows. Language models are used only for natural-language interaction, high-level task understanding, and exception support, keeping the critical fast path efficient. We implement a single qubit tune-up workflow as a demonstration and validation using real quantum device dataset. We also prove that the framework achieves quantitatively acceptable levels in terms of resource cost, LLM calling times and decision latency, enabling its practical deployment in large-scale quantum qubit measurement and control scenarios. This work presents a general workflow-oriented framework for QMC and provides evidence that rule-centered architectures are a promising design choice for scalable quantum-system calibration.

quant-ph↗

arXiv2026

Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing

Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models. However, most existing methods remain confined to single-turn settings, overlooking the more realistic scenario of multi-turn in-context editing, where users iteratively refine an image through a sequence of instructions. In this setting, a model must follow each new instruction while preserving accumulated session-level constraints, challenged by two coupled failure modes: long-context dilution, where sparse textual constraints become difficult to recover from growing interleaved image-text histories, and state contamination, where earlier editing mistakes degrade subsequent generations. We introduce Edit-R2, a novel reinforcement learning post-training framework for unified multimodal models. Edit-R2 reconstructs the operative session intent, which effectively consolidates scattered historical constraints into an explicit reasoning trace before each editing turn. It further enables multi-turn RL over both reasoning and generation through a unified objective that jointly optimizes intent reconstruction generation in discrete text space and flow-matching image generation in continuous latent space, while a trajectory filtering mechanism suppresses corrupted rollouts to stabilize training under state contamination. To support systematic evaluation, we introduce MICE-Bench, a large-scale benchmark for multi-turn in-context editing with automated metrics for instruction following (IF), content consistency (CC), and global awareness (GA) over accumulated session constraints. Experiments show that Edit-R2 substantially improves multi-turn in-context editing and achieves competitive performance compared against strong baselines.

cs.AI↗

arXiv2026

Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming

Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains a critical, under-explored safety concern, posing a significant safety risk to real-world deployment. Red teaming, or identifying environmental scenarios that elicit catastrophic behaviors, is an important step in ensuring the safe deployment of embodied AI agents. Reinforcement learning (RL) has emerged as a promising approach in automated red teaming that aims to uncover these vulnerabilities. However, standard RL-based adversaries often suffer from severe mode collapse due to their reward-maximizing nature, which tends to converge to a narrow set of trivial or repetitive failure patterns, failing to reveal the comprehensive landscape of meaningful risks. To bridge this gap, we propose a novel \textbf{D}iversity-\textbf{A}ware \textbf{E}mbodied \textbf{R}ed \textbf{T}eaming (\textbf{DAERT}) framework, to expose the vulnerabilities of VLAs against linguistic variations. Our design is based on evaluating a uniform policy, which is able to generate a diverse set of challenging instructions while ensuring its attack effectiveness, measured by execution failures in a physical simulator. We conduct extensive experiments across different robotic benchmarks against two state-of-the-art VLAs, including $\pi_0$ and OpenVLA. Our method consistently discovers a wider range of more effective adversarial instructions that reduce the average task success rate from 93.33\% to 5.85\%, demonstrating a scalable approach to stress-testing VLA agents and exposing critical safety blind spots before real-world deployment.

cs.RO↗

arXiv2026

Tunable Nonlocal $ZZ$ Interaction for Remote Controlled-Z Gates Between Distributed Fixed-Frequency Qubits

Scaling superconducting quantum processors toward fault-tolerant operation will likely require architectures that extend beyond monolithic chips. Modular processors connected by low-loss superconducting links provide a promising route, but implementing entangling gates between remote fixed-frequency qubits remains challenging. Here we propose a distributed architecture in which two synchronously controlled double-transmon couplers mediate the interaction between fixed-frequency transmons in separate packages connected by a 25-cm coaxial cable. The scheme activates a tunable nonlocal $ZZ$ interaction on demand while suppressing residual static coupling, allowing the superconducting link to function as a gate-native interconnect rather than solely as a state-transfer channel. Circuit-level simulations show an on/off ratio exceeding $10^6$ and a remote controlled-Z gate with a projected coherent fidelity of $99.99\%$ under experimentally relevant parameters. Open-system simulations further indicate that, within the representative Markovian noise model considered here, endpoint-qubit decoherence is the largest contribution to gate infidelity, while photon loss in the retained cable modes remains smaller but non-negligible. These results identify DTC-mediated tunable nonlocal coupling as a promising gate primitive for modular superconducting processors based on fixed-frequency qubits.

quant-ph↗

arXiv2026

The Extra Vanishing Structure and Nonlinear Stability of Multi-Dimensional Rarefaction Waves: The Geometric Weighted Energy Estimates

We study the resolution of discontinuous singularities in gas dynamics via multi-dimensional rarefaction waves. While the mechanism is well-understood in one spatial dimension, the rigorous construction in higher dimensions has remained a challenging open problem since Majda's proposal, primarily due to the characteristic nature of rarefaction fronts which leads to derivative losses in linearized estimates. In this paper, we establish the nonlinear stability of multi-dimensional rarefaction waves for the compressible Euler equations with ideal gas law. We prove that for initial data being small perturbations of the planar rarefaction wave in $H^s$ ($s > s_c$), there exists a unique global solution that converges asymptotically to the background rarefaction wave as $t \to \infty$. Our proof relies on a novel Geometric Weighted Energy Method (GWEM), which yields stable energy estimates without loss of derivatives in standard Sobolev spaces, overcoming the limitations of previous Nash-Moser schemes. A key ingredient is a detailed geometric description of the rarefaction wave fronts via the acoustical metric, where we identify a hidden extra vanishing structure in the top-order derivatives of the characteristic speed. This is the first paper in a series, providing the crucial a priori energy bounds. The existence of solutions and applications to the multi-dimensional Riemann problem will be addressed in the forthcoming companion paper.

math.AP↗

arXiv2026

A Fubini Theorem for Grothendieck Functional Integrals

This paper systematically studies the subset of continuous linear functionals on the projective tensor product of Banach spaces whose norms are bounded by Grothendieck's constant $K_G$. We term such functionals Grothendieck functional integrals. The integral is defined as a linear functional on the projective tensor product space that satisfies the boundedness condition $|\mu(x)| \leq K_G \|x\|_\pi$, where $K_G$ denotes Grothendieck's constant. We prove that such integrals admit a Hilbert space representation theorem and establish the corresponding abstract Fubini theorem to demonstrate that the order of integration may be interchanged. Furthermore, we extend this theory to the setting of multiple tensor products and provide integral representations in concrete function spaces. Our work offers a unified framework for bilinear and multilinear analysis, with a universal constant serving as the fundamental bound.

math.FA↗

arXiv2026

The Coupled Hitchin-He Equations: Integrable Deformations and Rigidity of the Moduli Space

We introduce the \emph{parameter-geometrization} to the Hitchin system, a paradigm embedding deformation parameters into geometry via the coupled Hitchin-He equations on a surface with boundary. A boundary term couples a second Higgs field $\psi$, recovering the classical system at $\alpha=0$. We prove a unique, smooth solution branch exists near $\alpha=0$ (Theorem A). The system is integrable, admitting a Lax pair (Theorem B). Crucially, the moduli space $\mathcal{M}_\alpha$ is analytically isomorphic to $\mathcal{M}_0$ for small $|\alpha|$, preserving the Hitchin fibration -- revealing a deep rigidity where all moduli are controlled by the primary Higgs field (Theorem C). Using the \emph{nonlinear embedding} technique that casts the deformed system into the form of a classical Higgs bundle system, whose integrability and geometry are well-understood, we extends the framework to compact K\"ahler manifolds (Theorem D).

math.DG↗

arXiv2025

GARDO: Reinforcing Diffusion Models without Reward Hacking

Fine-tuning diffusion models via online reinforcement learning (RL) has shown great potential for enhancing text-to-image alignment. However, since precisely specifying a ground-truth objective for visual tasks remains challenging, the models are often optimized using a proxy reward that only partially captures the true goal. This mismatch often leads to reward hacking, where proxy scores increase while real image quality deteriorates and generation diversity collapses. While common solutions add regularization against the reference policy to prevent reward hacking, they compromise sample efficiency and impede the exploration of novel, high-reward regions, as the reference policy is usually sub-optimal. To address the competing demands of sample efficiency, effective exploration, and mitigation of reward hacking, we propose Gated and Adaptive Regularization with Diversity-aware Optimization (GARDO), a versatile framework compatible with various RL algorithms. Our key insight is that regularization need not be applied universally; instead, it is highly effective to selectively penalize a subset of samples that exhibit high uncertainty. To address the exploration challenge, GARDO introduces an adaptive regularization mechanism wherein the reference model is periodically updated to match the capabilities of the online policy, ensuring a relevant regularization target. To address the mode collapse issue in RL, GARDO amplifies the rewards for high-quality samples that also exhibit high diversity, encouraging mode coverage without destabilizing the optimization process. Extensive experiments across diverse proxy rewards and hold-out unseen metrics consistently show that GARDO mitigates reward hacking and enhances generation diversity without sacrificing sample efficiency or exploration, highlighting its effectiveness and robustness.

cs.LG↗

arXiv2025

Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach

Vision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human teleoperation, scripted policies). However, since VLAs incorporate diverse data modes in the pre-training stage, and the finetuning dataset often contains demonstration data collected in a kinematically suboptimal or undesirable way, it exists redundant action modes that are irrelevant to the success action modes of the downstream task. Specifically, we observe a critical inference-time fragility among various sampled noises after supervised finetuning of pre-trained VLAs. In this paper, we attribute this instability to the distribution shift between the VLA policy and the policy induced by stable success modes of the downstream task dataset. Thus, we propose \textbf{TACO}, a test-time-scaling (TTS) framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks. The VLA models integrated with TACO can execute the actions with maximum pseudo-count from all sampled action chunks, thereby preventing distribution shifts while preserving the generalization ability of VLAs since the constraint is applied only during inference. Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits compared to RL update, especially for flow or diffusion-based VLAs which are difficult to perform RL update due to denoising process. Extensive experiments across four simulation benchmarks (RoboTwin2.0, Robotwin, LIBERO, SimplerEnv) and a dual-arm platform demonstrate that our method significantly improves the inference stability and success rates in downstream-task adaptations.

cs.RO↗

arXiv2025

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems

This paper proposes a machine learning-assisted channel estimation approach for massive MIMO systems, leveraging DNNs to outperform traditional LS and MMSE methods. In 5G and beyond, accurate channel estimation mitigates pilot contamination and high mobility issues that harm system reliability. The proposed DNN architecture includes multi-layer perceptrons with ReLU activation, 3 hidden layers (256, 128, 64 neurons respectively), uses Adam optimizer (learning rate 1e-4) and MSE loss function. It learns from pilot signals to predict channel matrices, achieving lower NMSE and BER across different SNR levels. Simulations use the COST 2100 public standard dataset (a well-recognized MIMO channel dataset for 5G, not synthetic datasets) with 10,000 samples of 4x4 MIMO channels under urban macro scenarios. Results show the DNN outperforms LS and MMSE by 3-5 dB in NMSE at medium SNR, with robust performance in high-mobility scenarios. The study evaluates metrics like NMSE vs. SNR, BER vs. SNR, and sensitivity to pilot length, antenna configurations, and computational complexity. The DNN has 2.3 GFlOPs computational complexity, 15.6k parameters, and 1.8 ms inference time on Raspberry Pi 4, verifying deployment feasibility. This work advances ML integration in wireless communications, facilitating efficient resource allocation and improved spectral efficiency in next-generation networks. Future work may use more real-world datasets and hybrid architectures for better generalization.

eess.SP↗

arXiv2025

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards

RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on policy optimization frameworks like PPO and GRPO, which follow generalized policy iteration that alternates between evaluating the current policy's value and improving the policy based on evaluation. While effective, they often suffer from training instability and diversity collapse, requiring complex heuristic tricks and careful tuning. We observe that standard RLVR in math reasoning can be formalized as a specialized finite-horizon Markov Decision Process with deterministic state transitions, tree-structured dynamics, and binary terminal rewards. Though large in scale, the underlying structure is simpler than general-purpose control settings for which popular RL algorithms (e.g., PPO) were developed, suggesting that several sophisticated techniques in existing methods may be reduced or even omitted. Based on this insight, we prove a surprising result: the optimal action can be recovered from the Q-function of a fixed uniformly random policy, thereby bypassing the generalized policy iteration loop and its associated heuristics. We introduce Random Policy Valuation for Diverse Reasoning (ROVER) to translate this principle into a practical and scalable algorithm for LLM math reasoning, a minimalist yet highly effective RL method that samples actions from a softmax over these uniform-policy Q-values. ROVER preserves diversity throughout training, allowing sustained exploration of multiple valid pathways. Across multiple base models and standard math reasoning benchmarks, ROVER demonstrates superior performance in both \textbf{quality} (\textbf{+8.2} on pass@1, \textbf{+16.8} on pass@256) and \textbf{diversity} (\textbf{+17.6\%}), despite its radical simplification compared to strong, complicated existing methods.

cs.LG↗

arXiv2025

EIFNet: Leveraging Event-Image Fusion for Robust Semantic Segmentation

Event-based semantic segmentation explores the potential of event cameras, which offer high dynamic range and fine temporal resolution, to achieve robust scene understanding in challenging environments. Despite these advantages, the task remains difficult due to two main challenges: extracting reliable features from sparse and noisy event streams, and effectively fusing them with dense, semantically rich image data that differ in structure and representation. To address these issues, we propose EIFNet, a multi-modal fusion network that combines the strengths of both event and frame-based inputs. The network includes an Adaptive Event Feature Refinement Module (AEFRM), which improves event representations through multi-scale activity modeling and spatial attention. In addition, we introduce a Modality-Adaptive Recalibration Module (MARM) and a Multi-Head Attention Gated Fusion Module (MGFM), which align and integrate features across modalities using attention mechanisms and gated fusion strategies. Experiments on DDD17-Semantic and DSEC-Semantic datasets show that EIFNet achieves state-of-the-art performance, demonstrating its effectiveness in event-based semantic segmentation.

cs.CV↗

arXiv2025

Spintronic Bayesian Hardware Driven by Stochastic Magnetic Domain Wall Dynamics

As artificial intelligence (AI) advances into diverse applications, ensuring reliability of AI models is increasingly critical. Conventional neural networks offer strong predictive capabilities but produce deterministic outputs without inherent uncertainty estimation, limiting their reliability in safety-critical domains. Probabilistic neural networks (PNNs), which introduce randomness, have emerged as a powerful approach for enabling intrinsic uncertainty quantification. However, traditional CMOS architectures are inherently designed for deterministic operation and actively suppress intrinsic randomness. This poses a fundamental challenge for implementing PNNs, as probabilistic processing introduces significant computational overhead. To address this challenge, we introduce a Magnetic Probabilistic Computing (MPC) platform-an energy-efficient, scalable hardware accelerator that leverages intrinsic magnetic stochasticity for uncertainty-aware computing. This physics-driven strategy utilizes spintronic systems based on magnetic domain walls (DWs) and their dynamics to establish a new paradigm of physical probabilistic computing for AI. The MPC platform integrates three key mechanisms: thermally induced DW stochasticity, voltage controlled magnetic anisotropy (VCMA), and tunneling magnetoresistance (TMR), enabling fully electrical and tunable probabilistic functionality at the device level. As a representative demonstration, we implement a Bayesian Neural Network (BNN) inference structure and validate its functionality on CIFAR-10 classification tasks. Compared to standard 28nm CMOS implementations, our approach achieves a seven orders of magnitude improvement in the overall figure of merit, with substantial gains in area efficiency, energy consumption, and speed. These results underscore the MPC platform's potential to enable reliable and trustworthy physical AI systems.

physics.app-ph↗

arXiv2025

Scaling Image and Video Generation via Test-Time Evolutionary Search

As the marginal cost of scaling computation (data and parameters) during model pre-training continues to increase substantially, test-time scaling (TTS) has emerged as a promising direction for improving generative model performance by allocating additional computation at inference time. While TTS has demonstrated significant success across multiple language tasks, there remains a notable gap in understanding the test-time scaling behaviors of image and video generative models (diffusion-based or flow-based models). Although recent works have initiated exploration into inference-time strategies for vision tasks, these approaches face critical limitations: being constrained to task-specific domains, exhibiting poor scalability, or falling into reward over-optimization that sacrifices sample diversity. In this paper, we propose \textbf{Evo}lutionary \textbf{Search} (EvoSearch), a novel, generalist, and efficient TTS method that effectively enhances the scalability of both image and video generation across diffusion and flow models, without requiring additional training or model expansion. EvoSearch reformulates test-time scaling for diffusion and flow models as an evolutionary search problem, leveraging principles from biological evolution to efficiently explore and refine the denoising trajectory. By incorporating carefully designed selection and mutation mechanisms tailored to the stochastic differential equation denoising process, EvoSearch iteratively generates higher-quality offspring while preserving population diversity. Through extensive evaluation across both diffusion and flow architectures for image and video generation tasks, we demonstrate that our method consistently outperforms existing approaches, achieves higher diversity, and shows strong generalizability to unseen evaluation metrics. Our project is available at the website https://tinnerhrhe.github.io/evosearch.

cs.CV↗

arXiv2025

Control-Oriented Modelling and Adaptive Parameter Estimation for Hybrid Wind-Wave Energy Systems

Hybrid wind-wave energy system, integrating floating offshore wind turbine and wave energy converters, has received much attention in recent years due to its potential benefit in increasing the power harvest density and reducing the levelized cost of electricity. Apart from the design complexities of the hybrid wind-wave energy systems, their energy conversion efficiency, power output smoothness and their safe operations introduce new challenges for their control system designs. Recent studies show that advanced model-based control strategies have the great potential to significantly improve their overall control performance. However the performance of these advanced control strategies rely on the computationally efficient control-oriented models with sufficient fidelity, which are normally difficult to derive due to the complexity of the hydro-, aero-dynamic effects and the couplings.In most available results, the hybrid wind-wave energy system models are established by using the Boundary Element Method, devoting to understanding the hydrodynamic responses and performance analysis. However, such models are complex and involved relatively heavy computational burden, which cannot be directly used for the advanced model-based control methods that are essential for improving power capture efficiency from implementing in practice. To overcome this issue, this paper proposes a control-oriented model of the hybrid windwave energy system with six degrees of freedom. First, ...

eess.SY↗

arXiv2025

Performance Evaluation of Large Language Models in Statistical Programming

The programming capabilities of large language models (LLMs) have revolutionized automatic code generation and opened new avenues for automatic statistical analysis. However, the validity and quality of these generated codes need to be systematically evaluated before they can be widely adopted. Despite their growing prominence, a comprehensive evaluation of statistical code generated by LLMs remains scarce in the literature. In this paper, we assess the performance of LLMs, including two versions of ChatGPT and one version of Llama, in the domain of SAS programming for statistical analysis. Our study utilizes a set of statistical analysis tasks encompassing diverse statistical topics and datasets. Each task includes a problem description, dataset information, and human-verified SAS code. We conduct a comprehensive assessment of the quality of SAS code generated by LLMs through human expert evaluation based on correctness, effectiveness, readability, executability, and the accuracy of output results. The analysis of rating scores reveals that while LLMs demonstrate usefulness in generating syntactically correct code, they struggle with tasks requiring deep domain understanding and may produce redundant or incorrect results. This study offers valuable insights into the capabilities and limitations of LLMs in statistical programming, providing guidance for future advancements in AI-assisted coding systems for statistical analysis.

stat.AP↗

arXiv2025

Pre-Trained Video Generative Models as World Simulators

Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often generate clips based on static prompts (e.g., text or images), limiting their ability to model interactive and dynamic scenarios. In this paper, we propose Dynamic World Simulation (DWS), a novel approach to transform pre-trained video generative models into controllable world simulators capable of executing specified action trajectories. To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module that seamlessly integrates into any existing model. Instead of focusing on complex visual details, we demonstrate that consistent dynamic transition modeling is the key to building powerful world simulators. Building upon this insight, we further introduce a motion-reinforced loss that enhances action controllability by compelling the model to capture dynamic changes more effectively. Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models, achieving significant improvements in generating action-controllable, dynamically consistent videos across games and robotics domains. Moreover, to facilitate the applications of the learned world simulator in downstream tasks such as model-based reinforcement learning, we propose prioritized imagination to improve sample efficiency, demonstrating competitive performance compared with state-of-the-art methods.

cs.CV↗

arXiv2024

Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner

Diffusion models have demonstrated their capabilities in modeling trajectories of multi-tasks. However, existing multi-task planners or policies typically rely on task-specific demonstrations via multi-task imitation, or require task-specific reward labels to facilitate policy optimization via Reinforcement Learning (RL). They are costly due to the substantial human efforts required to collect expert data or design reward functions. To address these challenges, we aim to develop a versatile diffusion planner capable of leveraging large-scale inferior data that contains task-agnostic sub-optimal trajectories, with the ability to fast adapt to specific tasks. In this paper, we propose SODP, a two-stage framework that leverages Sub-Optimal data to learn a Diffusion Planner, which is generalizable for various downstream tasks. Specifically, in the pre-training stage, we train a foundation diffusion planner that extracts general planning capabilities by modeling the versatile distribution of multi-task trajectories, which can be sub-optimal and has wide data coverage. Then for downstream tasks, we adopt RL-based fine-tuning with task-specific rewards to quickly refine the diffusion planner, which aims to generate action sequences with higher task-specific returns. Experimental results from multi-task domains including Meta-World and Adroit demonstrate that SODP outperforms state-of-the-art methods with only a small amount of data for reward-guided fine-tuning.

cs.LG↗