arXiv subjects

Haoran He

Publications and source records attributed to Haoran He.

At least 19 recordsLinked to original sources

arXiv2026

Logarithmic Bias of Zero-Noise Extrapolation under 1/f Noise

Zero-noise extrapolation estimates ideal quantum observables by amplifying noise and extrapolating the measured response. Its accuracy depends on whether the extrapolation model captures the physical effect of amplification, including correlations between repeated operations. Here we derive the response of complete multiqubit gate folding in the simultaneous presence of time-local Markovian noise and stationary finite-band 1/f noise. An ordered circuit kernel couples the observable to noise memory; exact block counting shows how folding samples correlations at increasing time separations. The resulting response contains an r^2 ln r coordinate, with a coefficient fixed by the noise spectrum and the integrated forward-inverse control response. Ordinary polynomial Richardson extrapolation leaves a calculable contribution from this coordinate; the three-node rule (1,3,5) retains 2.73 theta. We construct response-matched extrapolation, including a log-domain implementation, that cancels this contribution at the retained order. Explicit bounds separate the remaining control-shape, finite-band, higher-order, and native-offset errors. The theory applies to arbitrary finite multiqubit circuits within the stated control and noise model, and distinguishes removal of memory-induced bias from an unconditional guarantee of the ideal intercept. Single- and ten-qubit numerical examples illustrate the predicted correction and its response dependence.

quant-ph↗

arXiv2026

Reconfigurable Bus-based Quantum Router for Modular Superconducting Processors

Scaling superconducting quantum processors requires interconnects that provide both non-local connectivity and parallel entangling operations. While current quantum routers offer greater connectivity than nearest-neighbour topologies, their support for parallel, independently addressable two-qubit gates remains fundamentally limited, imposing severe compilation overheads that constitute a critical bottleneck. Here we introduce a bus-based reconfigurable quantum router that enables parallel controlled-$Z$ (CZ) gates for modular superconducting processors. Constructed from a flux-tunable SQUID network, the router selectively connects interface qubits to two shared buses, allowing destructive interference to suppress idle interactions while supporting two disjoint CZ gates in parallel. Full-system Hamiltonian simulations yield parallel-gate infidelities ranging from $7.9\times10^{-4}$ to $1.8\times10^{-3}$ under the operating conditions considered, and an open-system analysis identifies the coherence requirements for high-fidelity operation. We further assess the circuit-level consequences using hardware-aware compilation and resource-constrained scheduling. For the 36-qubit quantum Fourier transform (QFT), QAOA-MaxCut, and random-pairing circuits, the router reduces the median SWAP count by up to $34\%$ and the native CZ count by up to $20\%$ relative to a matched two-dimensional grid. Circuit-depth reductions are workload-dependent, reaching $20\%$ for QAOA-MaxCut but remaining negligible for the QFT despite its lower gate count. These results show that enhanced connectivity and schedulable parallelism provide complementary benefits for connectivity-intensive algorithms, establishing the router as a compiler-visible hardware resource and providing a scalable architectural pathway toward constructing highly connected modular superconducting quantum processors.

quant-ph↗

arXiv2026

V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization

Pretrained text-to-image models contain broad visual knowledge, yet they cannot reliably acquire or refine a specific visual identity from only a few references while preserving compositional control. Token-embedding methods are compact but often underfit identity, whereas adapter-based methods improve fidelity through persistent weight updates that can be costly to store and interfere when concepts are composed. We introduce V-Engram, a trigger-indexed external memory mechanism for Stable Diffusion 3.5. Each concept is assigned an explicit trigger that retrieves concept-specific memory, whose gated directions enter frozen text-encoder and MMDiT context states as relative residuals. Separating this memory from backbone adaptation enables prompt-selective and multi-concept access without merging model updates. Experiments show that V-Engram broadly matches DreamBooth-LoRA in overall subject fidelity while showing advantages in settings such as contextual subject preservation. Prompt-matched loading retrieves only matched entries, reducing most additional adaptation-state loading for a single-concept query. Qualitative results further demonstrate paired-trigger composition and same-class separation, while prompts without registered entries retain the frozen model's base behavior. Together, these results establish trigger-indexed memory as a modular interface for adding targeted visual evidence without rewriting the generator.

cs.AI↗

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

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

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 $π_0$ 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

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 $|μ(x)| \leq K_G \|x\|_π$, 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 $ψ$, recovering the classical system at $α=0$. We prove a unique, smooth solution branch exists near $α=0$ (Theorem A). The system is integrable, admitting a Lax pair (Theorem B). Crucially, the moduli space $\mathcal{M}_α$ is analytically isomorphic to $\mathcal{M}_0$ for small $|α|$, 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 Kähler 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

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↗

arXiv2025

Cryogenic in-memory computing using magnetic topological insulators

Machine learning algorithms have been proven effective for essential quantum computation tasks such as quantum error correction and quantum control. Efficient hardware implementation of these algorithms at cryogenic temperatures is essential. Here, we utilize magnetic topological insulators as memristors (termed magnetic topological memristors) and introduce a cryogenic in-memory computing scheme based on the coexistence of the chiral edge state and the topological surface state. The memristive switching and reading of the giant anomalous Hall effect exhibit high energy efficiency, high stability, and low stochasticity. We achieve high accuracy in a proof-of-concept classification task using four magnetic topological memristors. Furthermore, our algorithm-level and circuit-level simulations of large-scale neural networks demonstrate software-level accuracy and lower energy consumption for image recognition and quantum state preparation compared with existing magnetic memristor and CMOS technologies. Our results not only showcase a new application of chiral edge states but also may inspire further topological quantum physics-based novel computing schemes.

cond-mat.mes-hall↗