arXiv subjects

Ziwen Pan

Publications and source records attributed to Ziwen Pan.

At least 19 recordsLinked to original sources

arXiv2026

Two-Sided State-Space Models for Sequential Recommendation with Non-Random Multimodal Review Feedback

Two-sided digital platforms are inherently dynamic: user preferences shift, item popularity evolves, and reviews both reflect and drive these changes. Yet most sequential recommendation systems treat reviews as passive signals for updating user states, leaving two aspects underexplored. First, review generation is nonrandom, depending on evolving latent states of both users and items. Second, reviews can reshape item states, induce spillover across related items, and influence future user decisions. To address these gaps, we propose a two-sided state-space model (TS-SSM) for event-conditioned sequential recommendation. TS-SSM consists of three components: (1) a modality-missing-not-at-random fusion module that encodes review content and informative observation patterns; (2) user-state evolution with temporal variation and local graph message passing that uses related item states to refine user preferences; and (3) item-state evolution with asymmetric carryover of positive and negative review feedback. In experiments across six Amazon categories, TS-SSM increases Recall@20 over BSARec by 14.8%--18.8% and exceeds HM4SR by 11.7% on average. On Goodreads Fantasy, Recall@20 improves HM4SR from .5191 to .5847. Ablations highlight distinct contributions of observation patterns, local propagation, and item dynamics.

cs.IR↗

arXiv2026

Low-energy Muon-Nucleon scattering experiment: LUNE (White Paper)

The HIAF will provide high-intensity, high-quality muon beams with momenta from 0.5 to 7.5 GeV/c. This energy range is uniquely suited for precision muon scattering, bridging the gap between low-energy electron facilities and future high-energy lepton-ion colliders. In particular, HIAF will enable precision measurements with both positive and negative muon beams over a broad kinematic range, complementing existing electron-scattering facilities such as JLab, EicC and EIC. Based on HIAF muon source, the LUNE Collaboration has been established to address several fundamental questions in nuclear and particle physics, including the proton charge radius puzzle, nucleon electromagnetic structure, and the dynamics of quantum electrodynamics and hadronic interactions. The program proceeds in two phases, from elastic scattering to nucleon structure and beyond-Standard-Model searches. The experiment is expected to determine the proton charge radius with a precision of approximately 1.0\% using elastic muon-proton scattering. It will also perform systematic measurements of the proton electromagnetic form factors with both $\mu^+$ and $\mu^-$ beams, enabling precise studies of two-photon exchange effects and stringent tests of quantum electrodynamics. Beyond elastic scattering, LUNE will investigate TMD, gravitational form factors, and nuclear charge radii, providing new insights into the 3D structure of nucleons and nuclei. The experiment will further address important topics including Coulomb-distortion corrections, nuclear medium effects, and possible signatures of physics beyond the Standard Model. This white paper presents the scientific motivation, detector concept, expected performance, and long-term strategy of LUNE.

hep-ex↗

arXiv2026

Auditing Structured Randomness for Quantum Error Correction under a Bounded Cloud Fault Model

Cloud quantum processors compile submitted quantum error correction circuits and may colocate them with untrusted workloads. A fixed public encoder gives a fault-injection adversary a reusable target. Per-run reseeding changes the physical-to-logical fault map. Exact Haar-random encoders have exponential circuit cost. Efficient random ensembles provide average-moment guarantees and leave worst-case accepted corruption uncharacterized. We define accepted logical disturbance, an acceptance-weighted measure of harmful logical action in accepted results, and derive its exact Haar expectation. We evaluate a polynomial-cost seeded Clifford encoder family using dense linear algebra and gate-level stabilizer simulation against faults chosen before or after the encoder is known. Reseeding reduces mean accepted logical disturbance from 0.150 for faults chosen after learning each encoder to 0.020 for one fault chosen before it is known. The 86.7% reduction results from rejection. The fixed distance-three $[[5,1,3]]$ code corrects every tested weight-one Pauli, while 18.5% of sampled encoders in the selected ensemble satisfy exact quantum error correction. The measured reduction quantifies the integrity gain from reseeding and separates postselected detection from exact correction under explicit fault and attacker-knowledge models.

quant-ph↗

arXiv2026

Measurement and reload costs in direct quantum simulation of nonlinear waves

Quantum processors encode an N-point field in log_2(N) qubits, which renders nonlinear wave equations an important application for quantum simulation. Nonlinear evolution, however, requires the field values themselves, and these are not directly accessible without quantum measurement. Existing algorithms circumvent this measurement through linear embeddings and state copies, thereby obscuring its cost within the truncation order, the auxiliary dimensions, and the state preparation. In order to expose this cost, a hybrid split-step solver is proposed in which the field is measured, updated classically, and reloaded at every step, with all shots and gates accounted for in a single cost-and-error model. Since the entire field is available at every step, a property unavailable to linear approximations in strongly nonlinear regimes, the design of the solver reduces to a budgeting problem over the timestep, the polynomial degree, and the shot count. The coherent kernels of the solver are validated on superconducting hardware. An identical structure and bottleneck govern the viscous Burgers' equation in one and two dimensions. Because every step reads the full field, the quantum cost per step, measured as circuit depth multiplied by measurement shots, exceeds the classical cost with increasing grid size. The framework consequently identifies a coherent, measurement-free nonlinear update as the quantitative target that any end-to-end advantage must meet.

quant-ph↗

arXiv2026

RubriQ: Rubric-Guided Group Relative Policy Optimization for Constraint-Aware Quantum Circuit Synthesis

Designing fault-tolerant quantum circuits that are both algorithmically correct and hardware compatible remains a major bottleneck in the transition to scalable quantum computing. We introduce RubriQ, a scalable framework that formulates circuit synthesis as a large language model (LLM) code-generation task, optimized via group relative policy optimization (GRPO). Unlike conventional black-box neural critics, RubriQ employs a domain-grounded programmatic rubric as the reinforcement learning reward function, evaluating circuits for T-gate reduction, hardware topology compliance, and unitary fidelity. To support high-throughput training, RubriQ integrates GPU-accelerated CUDA-Q simulation directly into the reinforcement learning (RL) loop and is deployed on NERSC Perlmutter using DeepSpeed ZeRO2 across multinode NVIDIA A100 clusters. On benchmark tasks, RubriQ achieves a mean T-gate compression of 3.31x, significantly outperforming sparse-reward RL baselines (2.05x), converging 2-3x faster, and maintaining less than 1\% hardware-constraint violations. Validated on IBM and IonQ quantum processors, RubriQ establishes an automated, high-performance computing (HPC)-driven pipeline for generating hardware-ready, fault-tolerant quantum circuits at scale.

quant-ph↗

arXiv2026

Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness

Multimodal clinical records contain structured measurements and clinical notes recorded over time, offering rich temporal information about the evolution of patient health. Yet these observations are sparse, and whether they are recorded depends on the patient's latent condition. Observation patterns also differ across modalities, as structured measurements and clinical notes arise under distinct recording processes. While prior work has developed methods that accommodate missingness in clinical time series, how to extract and use the information carried by the observation process itself remains underexplored. We therefore propose a patient representation learning framework for multimodal clinical time series that explicitly leverages informative missingness. The framework combines (1) a multimodal encoder that captures signals from structured and textual data together with their observation patterns, (2) a Bayesian filtering module that updates a latent patient state over time from observed multimodal signals, and (3) downstream modules for offline treatment policy learning and patient outcome prediction based on the learned patient state. We evaluate the framework on ICU sepsis cohorts from MIMIC-III, MIMIC-IV, and eICU. It improves both offline treatment policy learning and adverse outcome prediction, achieving FQE 0.679 versus 0.528 for clinician behavior and AUROC 0.886 for post-72-hour mortality prediction on MIMIC-III.

cs.LG↗

arXiv2026

DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training

Large language models (LLMs) tuned for safety often avoid acknowledging demographic differences, even when such acknowledgment is factually correct (e.g., ancestry-based disease incidence) or contextually justified (e.g., religious hiring preferences). This identity-blindness yields incorrect responses, unnecessary refusals, or generic "equal-treatment" defaults. We study this via difference-awareness classification: given a question involving demographic groups, the task is not to answer directly, but to classify whether a correct answer requires recognizing group differences (yes) or whether groups should be treated identically (no). Crucially, fine-tuning for accuracy triggers harm drift: model-generated explanations become increasingly harmful as decision accuracy improves, whether by elaborating harmful content, introducing problematic assumptions, or failing to flag harms the baseline identified. To mitigate this, we introduce DART (Distill--Audit--Repair Training), which distills label-conditioned reasoning from a teacher, audits outputs for harm drift cases relative to baseline, and repairs problematic cases via severity-weighted fine-tuning. On eight benchmarks, DART improves Llama-3-8B-Instruct accuracy from 39.0% to 68.8%, with largest gains on equal-treatment prompts (11.3% -> 72.6%), while reducing harm drift cases by 72.6%. It also transfers to 280 open-ended real-world queries across medical, legal, policy, and educational domains, improving difference-appropriate responses from 39.8% to 77.5% while reducing refusals from 34.3% to 3.0%. Our results demonstrate that accuracy and safety need not conflict when explicit detection and repair mechanisms are in place.

cs.CL↗

arXiv2026

NNQA: Neural-Native Quantum Arithmetic for End-to-End Polynomial Synthesis

Hybrid classical quantum learning is often bottlenecked by communication overhead and approximation error from generic variational ansatzes. In this study, we introduce Neural Native Quantum Arithmetic (NNQA), which compiles classically learned nonlinear representations into precise quantum arithmetic composed of native unitary blocks. Theoretically, we prove that the universal approximation of quantum polynomial arithmetic can be realized by transforming a classical neural network into a quantum circuit, with the resulting error arising solely from measurement shot noise, thereby extending classical operator-level estimation guarantees into the quantum regime. Empirical validation on IBM Quantum Heron3 and IonQ Forte processors shows performance limited primarily by device noise without variational fine tuning: we achieve over 99.5% accuracy for polynomials up to degree 35 and demonstrate scalability on IonQ hardware up to 36 qubits and circuit depths of 70, reaching a negligible RMSE of 0.005. Overall, NNQA establishes a new paradigm of synthesizing quantum arithmetic for native quantum computation.

quant-ph↗

arXiv2025

Quantum Approximate Walk Algorithm

The encoding of classical to quantum data mapping through trigonometric functions within arithmetic-based quantum computation algorithms leads to the exploitation of multivariate distributions. The studied variational quantum gate learning mechanism, which relies on agnostic gradient optimization, does not offer algorithmic guarantees for the correlation of results beyond the measured bitstring outputs. Consequently, existing methodologies are inapplicable to this problem. In this study, we present a classical data-traceable quantum oracle characterized by a circuit depth that increases linearly with the number of qubits. This configuration facilitates the learning of approximate result patterns through a shallow quantum circuit (SQC) layout. Moreover, our approach demonstrates that the classical preprocessing of mid-quantum measurement data enhances the interpretability of quantum approximate optimization algorithm (QAOA) outputs without requiring full quantum state tomography. By establishing an inferable mapping between the classical input and quantum circuit outcomes, we obtained experimental results on the state-of-the-art IBM Pittsburgh hardware, which yielded polynomial-time verification of the solution quality. This hybrid framework bridges the gap between near-term quantum capabilities and practical optimization requirements, offering a pathway toward reliable quantum-classical algorithms for industrial applications.

quant-ph↗

arXiv2025

Quantum Data Representation via Circuit Partitioning and Reintegration

Quantum data encoding (QDE) enables faster com-putations than classical algorithms through superposition and en-tanglement. Circuit cutting and knitting are effective techniques for ameliorating current noisy quantum processing unit (QPUs) errors via a divide-and-conquer approach that splits quantum circuits into subcircuits and recombines them using classical postprocessing. Unfortunately, the existing QDE frameworks fail to consider quantum hardware limitations, such as the topology of the chip. Designing a computation model that supports the algorithm level of quantum computation and optimizes non-all-to-all connected quantum circuit simulations remains underde-veloped. In this study, we introduce shardQ, a method that leverages the SparseCut algorithm with matrix product state (MPS) compilation and a global knitting technique to mitigate the quantum error rates. This method elucidates the optimal trade-off between the computational time and error rate for quantum encoding with a theoretical proof, evidenced by an ablation analysis using an IBM Heron-type QPUs with 15% error reduction. This study also presents the results of quantum image encoding readiness. The proposed model advances the current quantum computation towards the fault-tolerant regime as QDE is the input of grand unified quantum algorithms.

quant-ph↗

arXiv2025

AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models

How do inference time and latent computations enable large language models (LLMs) to solve multi-step reasoning problems? We introduce AlgoTrace, a framework for tracing and steering algorithmic operations in the model latent space for multi-step reasoning. We operationalize primitives by clustering latent activations of the model when solving four benchmarks: Traveling Salesperson Problem (TSP), 3SAT, AIME, and Graph Navigation. We annotate the clusters using their corresponding tokens in the reasoning trace. We then apply function vector methods to extract primitive vectors as reusable compositional building blocks of reasoning. We find that a) injecting a primitive vector into models (Phi, Qwen, Llama) elicits the associated algorithmic operation in the reasoning trace, b) injecting primitives can steer behavior across tasks, c) primitive vectors can be composed through algebraic operations, revealing a geometric logic in activation space, and d) a fine-tuned model exhibits improved composition of primitives (Phi-4-Reasoning vs. Phi-4). These findings demonstrate that LLM reasoning can be understood as a walk through algorithmic primitives in the latent space governed by compositional geometry. These primitives transfer across tasks, and reasoning finetuning strengthens algorithmic generalization and composition across domains.

cs.LG↗

arXiv2025

Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness

Clinical notes contain rich patient information, such as diagnoses or medications, making them valuable for patient representation learning. Recent advances in large language models have further improved the ability to extract meaningful representations from clinical texts. However, clinical notes are often missing. For example, in our analysis of the MIMIC-IV dataset, 24.5% of patients have no available discharge summaries. In such cases, representations can be learned from other modalities such as structured data, chest X-rays, or radiology reports. Yet the availability of these modalities is influenced by clinical decision-making and varies across patients, resulting in modality missing-not-at-random (MMNAR) patterns. We propose a causal representation learning framework that leverages observed data and informative missingness in multimodal clinical records. It consists of: (1) an MMNAR-aware modality fusion component that integrates structured data, imaging, and text while conditioning on missingness patterns to capture patient health and clinician-driven assignment; (2) a modality reconstruction component with contrastive learning to ensure semantic sufficiency in representation learning; and (3) a multitask outcome prediction model with a rectifier that corrects for residual bias from specific modality observation patterns. Comprehensive evaluations across MIMIC-IV and eICU show consistent gains over the strongest baselines, achieving up to 13.8% AUC improvement for hospital readmission and 13.1% for ICU admission.

cs.LG↗

arXiv2025

Improving Muon Scattering Tomography Performance With A Muon Momentum Measurement Scheme

Muon imaging, especially muon scattering tomography (MST), has recently garnered significant attention. MST measures the magnitude of muon scattering angles inside an object, which depends not only on the material properties but also on the muon momentum. Due to the difficulty of simultaneous measurement of momentum, it was neglected and taken as a constant in multiple MST reconstruction algorithms. Recently, an experimental measurement scheme has emerged that is feasible in engineering, but it requires many layers of detectors to approach the true momentum. From this, we proposed both an algorithm to incorporating momentum into MST, and a scheme to determine the thresholds of Cherenkov detectors. This novel scheme, termed the "equi-percentage scheme", sets momentum thresholds for Cherenkov detector layers based on cosmic muon momentum distribution. Results showed our approach delivers noticeable enhancement in reconstructed image quality even with only two detector layers, reaching near-saturation performance with four layers. This study proves that momentum measurement significantly enhances short-duration MST, and that substantial improvement can be achieved with relatively coarse momentum measurement using 2-4 layers of Cherenkov detectors.

physics.ins-det↗

arXiv2025

Vectorized Attention with Learnable Encoding for Quantum Transformer

Vectorized quantum block encoding provides a way to embed classical data into Hilbert space, offering a pathway for quantum models, such as Quantum Transformers (QT), that replace classical self-attention with quantum circuit simulations to operate more efficiently. Current QTs rely on deep parameterized quantum circuits (PQCs), rendering them vulnerable to QPU noise, and thus hindering their practical performance. In this paper, we propose the Vectorized Quantum Transformer (VQT), a model that supports ideal masked attention matrix computation through quantum approximation simulation and efficient training via vectorized nonlinear quantum encoder, yielding shot-efficient and gradient-free quantum circuit simulation (QCS) and reduced classical sampling overhead. In addition, we demonstrate an accuracy comparison for IBM and IonQ in quantum circuit simulation and competitive results in benchmarking natural language processing tasks on IBM state-of-the-art and high-fidelity Kingston QPU. Our noise intermediate-scale quantum friendly VQT approach unlocks a novel architecture for end-to-end machine learning in quantum computing.

quant-ph↗

arXiv2025

A mobile high spatial-resolution Muography instrument based on large-area Micromegas detectors

Muon radiography is an imaging technique based on muon absorption in matter that allows measurement of internal details in hidden objects or structures. This technique relies on measuring cosmic-ray muons tracks accurately, which reflects the incoming muon flux from both the target object and the open sky. In this paper, we report on the construction of a high spatial resolution muography instrument based on Micromegas detectors. Using four layers of 400 mm ${\times}$ 400 mm Micromegas detectors, channel multiplexing circuits, and the versatile readout system, a moveable muography instrument named $\mu$STC-R400 was designed and constructed. Results show that the channel multiplexing circuits can resolve hit positions correctly, and the spatial resolution of the detector is approximately 190 ${\mu}$m. Experiments were conducted at an under-construction subway tunnel and outdoors near a mountain, demonstrating the ${\mu}$STC-R400's ability to maintain high spatial resolution outside the laboratory and its robustness in harsh environments.

physics.ins-det↗

arXiv2025

CareLab at #SMM4H-HeaRD 2025: Insomnia Detection and Food Safety Event Extraction with Domain-Aware Transformers

This paper presents our system for the SMM4H-HeaRD 2025 shared tasks, specifically Task 4 (Subtasks 1, 2a, and 2b) and Task 5 (Subtasks 1 and 2). Task 4 focused on detecting mentions of insomnia in clinical notes, while Task 5 addressed the extraction of food safety events from news articles. We participated in all subtasks and report key findings across them, with particular emphasis on Task 5 Subtask 1, where our system achieved strong performance-securing first place with an F1 score of 0.958 on the test set. To attain this result, we employed encoder-based models (e.g., RoBERTa), alongside GPT-4 for data augmentation. This paper outlines our approach, including preprocessing, model architecture, and subtask-specific adaptations

cs.CL↗

arXiv2025

Test of LGAD as Potential Next-Generation {\mu}SR Spectrometer Detectors

Muon Spin Rotation/Relaxation/Resonance ($\mu$SR) is a versatile and powerful non-destructive technology for investigating the magnetic properties of materials at the microscopic level. The $\mu$SR technique typically utilizes fully spin polarized beams of positive muons generated at particle accelerator facilities and measures the evolution of the muon spin polarization inside a sample to extract information about the local magnetic environment in materials. With the development of accelerator technologies, intensities of muon beams are being continuously improved, which will cause a pile-up problem to the $\mu$SR spectrometer. The first muon source in China, named MELODY, is currently under construction and will be a pulsed source of muons operated at a repetition frequency of only 1 Hz due to limitations of the accelerator system at CSNS. Consequently, there is a strong motivation to operate MELODY at significantly higher muon intensities. This necessitates an upgrade of the detector system inside the spectrometer, which should be smaller and faster to accommodate the increased intensity per pulse of muons. The Low Gain Avalanche Diode (LGAD), characterized by a typical pulse width of 2 ns and a segmentation size in the centimeters range, has the potential to significantly improve the counting rates of $\mu$SR spectrometers that utilize a high intensity pulsed muon source. Thus, it is expected that the LGAD detector is a promising candidate to enhance the performance of $\mu$SR spectrometers at the new MELODY muon source.To validate this, tests on the LGAD were conducted at the ISIS pulsed muon source at the Rutherford Appleton Laboratory, UK. This paper will describe the setup of the candidate LGAD devices and the subsequent analysis of the experiment data.

physics.ins-det↗

arXiv2025

Correlation-Driven $d$-Wave Superconducting Dome from Pseudogap Spectral Reconstruction

Previous theoretical studies [Nat. Phys. {\bf 16}, 1175 (2020)] based on the Hatsugai-Kohmoto model have examined the stability of $s$-wave superconductivity in strongly correlated systems, demonstrating that correlations alone can substantially modify superconducting behavior. Motivated by this perspective, but going beyond these studies, we perform self-consistent microscopic calculations of $d$-wave superconductivity in strongly correlated systems by employing an exactly solvable correlated model that hosts a pseudogap phase and a partially flat band [Phys. Rev. Lett. {\bf 133}, 166501 (2024)]. We show that pseudogap correlations and superconducting order affect the low-energy spectrum in qualitatively different ways: the former leads to a momentum-localized suppression of spectral weight, whereas the latter induces a coherent reorganization of quasiparticle excitations. Moreover, we demonstrate that the interplay between superconducting order and pseudogap correlations naturally generates a superconducting dome in the temperature-doping phase diagram, with optimal doping located near the quantum critical point separating the pseudogap and metallic phases. Furthermore, $d_{x^2-y^2}$-wave superconductivity is found to be remarkably robust, remaining energetically dominant over both $d_{xy}$-wave and $s$-wave pairing channels across a wide doping range. Our results offer a potential route for a direct and controlled connection between pseudogap correlations and the emergence of the superconducting dome in cuprates.

cond-mat.str-el↗