arXiv subjects

Chuan Wang

Publications and source records attributed to Chuan Wang.

At least 19 recordsLinked to original sources

arXiv2026

Exact and Asymptotically Complete Robust Verifications of Neural Networks via Ising Solvers

We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations. For piecewise activations (both continuous piecewise-linear and discrete piecewise-constant), the Exact Logarithmic Piecewise Model (Log-PW) provides an exact, sound, and complete formulation with a state-optimal logarithmic encoding, reducing the binary variables per neuron from linear $O(κ)$ to information-theoretically minimal logarithmic complexity $O(\lceil \log_2 κ\rceil)$ via logarithmic SOS2 (Log-PWL) and SOS1 (Log-PWC) constraints. For general element-wise activations, the Asymptotic Step-Envelope Model (Step-Env) leverages Log-PWC to construct sound, refinable endpoint enclosures. An exact monotonic reduction based on Jordan decomposition further extends this framework to arbitrary non-monotonic activations. We further develop a hybrid Benders solver with output-sensitive iteration bounds, leveraging a Helly-based conflict compression theory to avoid generic exponential cut explosion. In particular, for shallow networks with fixed input dimension, this establishes an unconditionally polynomial Benders iteration complexity in network size. Interval pruning, certificate transfer for pruned networks, and layerwise classical--Ising partitioning further reduce spin requirements. Experiments demonstrate exact certification fidelity for piecewise-linear networks and near-reference accuracy for non-linear activations under compact spin budgets. On MNIST benchmarks, Log-PW halves binary decision spins over One-Hot formulations, while Helly-based cuts achieve up to a $13.41\times$ speedup and an $87.6\%$ reduction in master queries over standard baselines.

cs.LG↗

arXiv2026

High-Resolution Sensing via Quantum States Discrimination

High-resolution sensing plays a significant role in scientific research and industrial production, but the practical implementation is constrained by the physical mechanisms of the sensors. To address the critical limitation, we propose a high-resolution sensing approach based on quantum state discrimination. Distinct from conventional strategies, the proposed approach constructs measurement operators in the orthogonal complement space rather than eigenspace of the eigenstate, thereby notably improving the discriminability among quantum states. Moreover, the experimental results via an optical microcavity demonstrate a potential sensing resolution of 4 $\times$ 10\textsuperscript{-6} \degree C and 18 p$ε$ respectively for temperature and strain, and further verify the feasibility of simultaneous sensing of the two parameters. This work establishs a universal approach for high-resolution sensing, and may be extended to different sensing platforms across various application scenarios.

physics.optics↗

arXiv2026

PII-TRACE: A Benchmark for Context-Aware PII Detection in Multi-Turn LLM Conversations

LLM assistants and agentic systems log long multi-turn conversations. AI providers often scan these conversations for Personally Identifiable Information (PII) and mask the PII before storing or processing conversation data. Yet most PII detectors and benchmarks target self-contained records rather than cross-turn evaluation. To evaluate PII detection across turns in multi-turn conversations, we introduce PII-TRACE (Tracing Recurring PII Across Conversational Exchanges), to our knowledge the first PII benchmark to assess whether detectors identify PII in conversational contexts and cover every mention of a recurring identifier across turns. PII-TRACE contains 13,148 synthetic multi-turn dialogues in 13 languages with character-level spans and identifier clusters. Across eleven baselines, including frontier LLMs, no detector achieves full entity-level coverage without substantial false positives on PII-free conversations, and single-pass reading loses a third of the gold characters on long dialogues. To close this gap, we introduce PII-Tracer, a compact 0.6B-parameter detector trained with conversation-level supervision. PII-Tracer attains the highest entity-level coverage of any system we evaluate and also performs strongly on standard single-record benchmarks.

cs.CL↗

arXiv2026

Towards Provable and Scalable Training of Quantized Neural Networks with Ising Optimization

Training quantized neural networks remains fundamentally challenging due to non-convex loss landscapes and discrete parameter spaces. We introduce an exact Quadratic Constrained Binary Optimization (QCBO) framework with provable guarantees. We first characterize the stratified topology of network zero-loss level sets: generic interior strata are smooth, yet globally optimal components can remain disconnected even under overparameterization. To address this non-convex obstruction, we compile finite-depth architectures with parameter codebooks and Forward Interval Propagation (FIP)-bounded states into bounded QCBOs, yielding an exact completely positive convex formulation that preserves the global discrete optimum with zero relaxation gap. To overcome monolithic sample scaling, we formulate sample-wise Decomposed Lower-Bound Optimization (DLBO) to reduce each Ising call from dataset to single-sample scale. The DLBO moment hierarchy also forms a Hamiltonian-locality hierarchy, with order two giving an auxiliary-free pairwise QUBO oracle and higher orders trading interaction locality for tighter bounds. Strictly feasible discrete parameters are recovered via Spectral--ADMM and randomized rounding. Experiments on a coherent Ising machine achieve $94.95\%$ accuracy on binary Fashion-MNIST (coats vs. sandals) at 1.1-bit precision, demonstrating resilience against low-bit representational collapse. Multi-class DLBO evaluations on 3-class Fashion-MNIST, 3-class Wine, and 3-class Digits further validate scalable convergence.

cs.LG↗

arXiv2026

Quantum Advantage with Adaptive Shallow Circuits

Quantum advantage is widely expected to require sufficiently deep circuits, where correlations and global computational structure can grow beyond the reach of efficient classical simulation. This expectation is especially stark for constant-depth circuits with local readout: the expectation value of any fixed local observable lies within a bounded backward lightcone and is therefore classically tractable. Here we show that measurement feedback changes this picture. We establish a strict hierarchy of computational power: at fixed coherent depth, increasing the number of feedback outcomes strictly enlarges the class of functions accessible through a local expectation value. The two ends of this hierarchy exhibit distinct computational regimes. With logarithmic feedback, local expectation values for product-state inputs are efficiently classically simulable. Polynomial feedback, by contrast, enables an explicit family of adaptive shallow circuits to encode prime-field discrete logarithm problem~(DLP) into a fixed single-qubit expectation. Assuming the standard worst-case classical hardness of DLP, estimating this expectation value is classically hard. These results reveal a feedback-driven complexity transition, with further implications for resource lower bounds on DLP and the complexity of local-observable estimation under area-law entanglement. Our results open a new route to quantum advantage with shallow quantum circuits.

quant-ph↗

arXiv2026

OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review

LLM-based code review agents promise scalable, always-on review, yet current systems suffer from two intertwined weaknesses: (1) non-determinism--unbounded tool use makes review outcomes unstable, and (2) context locality--the reviewer's access remains bounded to the diff, capping discoverable issue depth. Both give rise to three challenges: misaligned context retrieval, a coherence-efficiency trade-off in multi-file pull requests, and hallucinated comments that erode trust. To address these, we introduce OpenCodeReview, built on deterministic engineering for uncertain agents: rather than granting maximal freedom, we inject determinism at three deliberate pipeline points. Rule-Guided Dispatch uses a multi-layer rule system to deterministically select files and review criteria, eliminating variability of agent-driven triage. Grounded File Review replaces free-form exploration with a curated tool set exposed through a ReAct loop, while file-level parallel SubAgents balance context coherence against efficiency and recover cross-file dependencies on demand. Independent Reflection introduces a falsification-first filter under an asymmetric information boundary--the reflector sees only the diff, not the agent's tool-augmented exploration--removing hallucinated comments without self-reinforcing bias, improving precision while preserving recall. On AACR-Bench (200 real-world PRs, 10 languages, 1,505 expert-verified comments), OpenCodeReview outperforms mainstream coding agents (e.g., Claude Code and Codex) across six LLM backends, achieving up to 2.17x higher SEM-F1 (25.10% vs. 11.57%) while consuming 5-15x fewer tokens. We open-source OpenCodeReview at https://github.com/alibaba/open-code-review.

cs.SE↗

arXiv2026

Efficient Noisy Quantum State and Process Tomography

Efficiently characterizing large quantum states and processes is a central yet notoriously challenging task in quantum information science, as conventional tomography methods typically require resources that grow exponentially with system size. Here, we introduce a structure-agnostic learning framework for noisy $n$-qubit quantum circuits under~i.i.d.~single-qubit noise. We first prove that quantum states with unital noise channels admit an efficient learnable representation in the logarithmic-depth regime. We then extend this framework to quantum process tomography under constant noise, deriving a unified protocol that applies to both unital and non-unital noisy channels and retains efficient guarantees for logarithmic-depth circuits. This process-learning formulation is input-agnostic and imposes no distributional assumptions on the input quantum states. We further study a more general regime with arbitrary noise strength. In this setting, low-weight Pauli propagation induces a terminal truncation whose threshold depends logarithmically on the inverse accuracy, leading to quasi-polynomial complexity and near-unit success probability in the average case. In contrast to the preceding two results, this arbitrary-noise guarantee does not impose any restriction on the circuit depth, and therefore covers arbitrary-depth circuits, including both the noiseless limit ($γ= 0$) and the strong-decoherence regime ($γ= Θ(1)$). Numerical simulations of two-dimensional Hamiltonian dynamics further demonstrate the accuracy and robustness of the approach, including for structured circuits beyond the random-circuit setting assumed in the theoretical analysis. These results provide a scalable and practically relevant route toward characterizing large-scale noisy quantum devices, addressing a key bottleneck in the development of quantum technologies.

quant-ph↗

arXiv2026

Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning

The rapid evolution of artificial intelligence has led to substantial advances in deep neural networks. Nonetheless, conventional GPU-based training remains highly energy-demanding, motivating the exploration of physical dynamics and compatible energy-based learning schemes, such as equilibrium propagation (EP). EP-based training, however, frequently suffers from convergence to local minima due to phase-space contraction. Here we introduce an Ising-dynamics-inspired equilibrium-propagation framework in which dissipative Hopfield relaxation is replaced by an extended phase-space dynamics with conjugate variables. The resulting training paradigm keeps the local two-phase learning rule of EP while changing the physical route by which neural states reach equilibrium. We show that this dynamics lowers effective energy barriers, accelerates convergence, improves noise robustness, and trains deep convolutional Hopfield networks on MNIST, FashionMNIST, and CIFAR-10 with performance comparable to backpropagation.

cs.LG↗

arXiv2026

Optimizing Energy-based Neural Network Training with Coherent Ising Machine

While Ising machines serve as advanced physical solvers for the Ising model,enabling applications in combinatorial optimization and neural network training,their scalability for large-scale neural networks remains constrained by hardware connectivity limitations and suboptimal training methodologies. In this work,we leverage a Coherent Ising Machine (CIM) to train an energy-based neural network using Equilibrium Propagation, achieving performance comparable to existing software-based implementations. We further enhance the algorithm by integrating the Adam optimizer to solve for the ground state of a Hopfield energy network, significantly improving convergence speed and solution accuracy. Additionally, we demonstrate the scalability of our approach across deeper network architectures and convolutional operations. Our results highlight the potential of CIM dynamics as a scalable platform for training complex neural networks, offering a pathway toward energy-efficient implementations via analog circuits, optoelectronics, or integrated photonics. This work establishes a novel physical framework for next-generation AI hardware development.

cs.LG↗

arXiv2026

Quantum-inspired Bayesian probability algorithm for nuclear mass predictions

In this study, a novel quantum-inspired Bayesian probability (QIBP) algorithm, informed by quantum dynamics, is proposed to improve the predictions of nuclear mass from theoretical models. Within the QIBP framework, residuals between the theoretical and experimental mass values are mapped into wave functions in Hilbert space. The corresponding potentials are obtained by solving the Schrödinger equation. Assuming that the residuals follow a Boltzmann distribution, the prior and likelihood probability density functions (PDFs) can be obtained from potentials. Finally, the Bayesian theorem is applied to derive the posterior PDF for estimating the target nuclear mass residuals. In global optimization, after employing the QIBP algorithm, the standard deviations of the WS4 model and the HFB model with the SLy4 parameter set are reduced from 0.273 MeV and 5.250 MeV to 0.149 MeV and 0.324 MeV, respectively. In extrapolation analysis, the QIBP algorithm also effectively improves both models, indicating robust extrapolation capability. In addition, extrapolation based on the synthetic experimental set shows that the QIBP algorithm performs well near the known region and remains effective for most nuclides toward the drip lines. Furthermore, the QIBP algorithm is applied to predict $α$-decay energies of Ra and Es isotopes, and the shell effects manifested in these isotopes are analyzed. This study validates the feasibility of quantum machine learning in nuclear mass research and demonstrates that the proposed algorithm can accurately describe nuclear masses, with potential applications in other areas of nuclear physics.

nucl-th↗

arXiv2026

CTQWformer: A CTQW-based Transformer for Graph Classification

Graph Neural Networks (GNN) and Transformer-based architectures have achieved remarkable progress in graph learning, yet they still struggle to capture both global structural dependencies and model the dynamic information propagation. In this paper, we propose CTQWformer, a hybrid graph learning framework that integrates continuous-time quantum walks (CTQW) with GNN. CTQWformer employs a trainable Hamiltonian that fuses graph topology and node features, enabling physically grounded modeling of quantum walk dynamics that captures rich and intricate graph structure information. The extracted CTQW-based representations are incorporated into two complementary modules:(i) a Graph Transformer module that embeds final-time propagation probabilities as structural biases in the self-attention mechanism, and (ii) a Graph Recurrent Module that captures temporal evolution patterns with bidirectional recurrent networks. Extensive experiments on benchmark graph classification datasets demonstrate that CTQWformer outperforms graph kernel and GNN-based methods, demonstrating the potential of integrating quantum dynamics into trainable deep learning frameworks for graph representation learning. To the best of our knowledge, CTQWformer is the first hybrid CTQW-based Transformer, integrating CTQW-derived structural bias with temporal evolution modeling to advance graph learning.

cs.LG↗

arXiv2026

LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction

Scaling Transformer-based click-through rate (CTR) models by stacking more parameters brings growing computational and storage overhead, creating a widening gap between scaling ambitions and the stringent industrial deployment constraints. We propose LoopCTR, which introduces a loop scaling paradigm that increases training-time computation through recursive reuse of shared model layers, decoupling computation from parameter growth. LoopCTR adopts a sandwich architecture enhanced with Hyper-Connected Residuals and Mixture-of-Experts, and employs process supervision at every loop depth to encode multi-loop benefits into the shared parameters. This enables a train-multi-loop, infer-zero-loop strategy where a single forward pass without any loop already outperforms all baselines. Experiments on three public benchmarks and one industrial dataset demonstrate state-of-the-art performance. Oracle analysis further reveals 0.02--0.04 AUC of untapped headroom, with models trained with fewer loops exhibiting higher oracle ceilings, pointing to a promising frontier for adaptive inference.

cs.IR↗

arXiv2026

EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval

Text-video retrieval tasks have seen significant improvements due to the recent development of large-scale vision-language pre-trained models. Traditional methods primarily focus on video representations or cross-modal alignment, while recent works shift toward enriching text expressiveness to better match the rich semantics in videos. However, these methods use only interactions between text and frames/video, and ignore rich interactions among the internal frames within a video, so the final expanded text cannot capture frame contextual information, leading to disparities between text and video. In response, we introduce Energy-Aware Fine-Grained Relationship Learning Network (EagleNet) to generate accurate and context-aware enriched text embeddings. Specifically, the proposed Fine-Grained Relationship Learning mechanism (FRL) first constructs a text-frame graph by the generated text candidates and frames, then learns relationships among texts and frames, which are finally used to aggregate text candidates into an enriched text embedding that incorporates frame contextual information. To further improve fine-grained relationship learning in FRL, we design Energy-Aware Matching (EAM) to model the energy of text-frame interactions and thus accurately capture the distribution of real text-video pairs. Moreover, for more effective cross-modal alignment and stable training, we replace the conventional softmax-based contrastive loss with the sigmoid loss. Extensive experiments have demonstrated the superiority of EagleNet across MSRVTT, DiDeMo, MSVD, and VATEX. Codes are available at https://github.com/draym28/EagleNet.

cs.CV↗

arXiv2026

Investigating Lipkin-Meshkov-Glick Model and Criticality-Enhanced Metrology in a Coherent Ising Machine

Quantum criticality has received extensive attention due to its ability to significantly enhance quantum sensing. But its realization and control in many-body quantum systems remain challenging. We present an effective scheme to simulate the Lipkin-Meshkov-Glick (LMG) model using a coherent Ising machine (CIM) composed of a network of degenerate optical parametric oscillators (DOPO). In our work, the spin variables of the LMG model are mapped onto the phases of DOPO pulses, and the spin-spin interactions are realized by all-to-all couplings among them. Through our investigation of the critical behavior in the antiferromagnetically coupled LMG model in the thermodynamic limit, i.e., $N\rightarrow\infty$, and its application in quantum sensing near the critical point, we verify that the CIM does not only effectively capture the second-order quantum phase transition (QPT) at the critical point but also reconstructs its complete phase diagram under ferromagnetic coupling. Furthermore, we demonstrate how the critical dynamics of this simulation platform can be utilized for quantum-enhanced metrology, achieving a measurement precision that diverges near the critical point of the LMG model. These results highlight the capability of the CIM as a flexible experimental platform for investigating the QPT in the fundamental quantum magnetic models, providing valuable insights into quantum simulation and critical phenomena.

quant-ph↗

arXiv2025

ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling

Industrial recommender systems face two fundamental limitations under the log-driven paradigm: (1) knowledge poverty in ID-based item representations that causes brittle interest modeling under data sparsity, and (2) systemic blindness to beyond-log user interests that constrains model performance within platform boundaries. These limitations stem from an over-reliance on shallow interaction statistics and close-looped feedback while neglecting the rich world knowledge about product semantics and cross-domain behavioral patterns that Large Language Models have learned from vast corpora. To address these challenges, we introduce ReaSeq, a reasoning-enhanced framework that leverages world knowledge in Large Language Models to address both limitations through explicit and implicit reasoning. Specifically, ReaSeq employs explicit Chain-of-Thought reasoning via multi-agent collaboration to distill structured product knowledge into semantically enriched item representations, and latent reasoning via Diffusion Large Language Models to infer plausible beyond-log behaviors. Deployed on Taobao's ranking system serving hundreds of millions of users, ReaSeq achieves substantial gains: >6.0% in IPV and CTR, >2.9% in Orders, and >2.5% in GMV, validating the effectiveness of world-knowledge-enhanced reasoning over purely log-driven approaches.

cs.IR↗

arXiv2025

A versatile coherent Ising computing platform

Coherent Ising Machines (CIMs) have emerged as a hybrid form of quantum computing devices designed to solve NP-complete problems, offering an exciting opportunity for discovering optimal solutions. Despite challenges such as susceptibility to noise-induced local minima, we achieved notable advantages in improving the computational accuracy and stability of CIMs. We conducted a successful experimental demonstration of CIM via femto-second laser pumping that integrates optimization strategies across optical and structural dimensions, resulting in significant performance enhancements. The results are particularly promising. An average success rate of 55% was achieved to identify optimal solutions within a Mobius Ladder graph comprising 100 vertices. Compared with other alternatives, the femto-second pulse results in significantly higher peak power, leading to more pronounced quantum effects and lower pump power in optical fiber based CIMs. In addition, we have maintained an impressive success rate for a continuous period of 8 hours, emphasizing the practical applicability of CIMs in real-world scenarios. Furthermore, our research extends to the application of these principles in practical applications such as molecular docking and credit scoring. The results presented substantiate the theoretical promise of CIMs, paving the way for their integration into large-scale practical applications.

quant-ph↗

arXiv2025

NeuMatC: A General Neural Framework for Fast Parametric Matrix Operation

Matrix operations (e.g., inversion and singular value decomposition (SVD)) are fundamental in science and engineering. In many emerging real-world applications (such as wireless communication and signal processing), these operations must be performed repeatedly over matrices with parameters varying continuously. However, conventional methods tackle each matrix operation independently, underexploring the inherent low-rankness and continuity along the parameter dimension, resulting in significantly redundant computation. To address this challenge, we propose \textbf{\textit{Neural Matrix Computation Framework} (NeuMatC)}, which elegantly tackles general parametric matrix operation tasks by leveraging the underlying low-rankness and continuity along the parameter dimension. Specifically, NeuMatC unsupervisedly learns a low-rank and continuous mapping from parameters to their corresponding matrix operation results. Once trained, NeuMatC enables efficient computations at arbitrary parameters using only a few basic operations (e.g., matrix multiplications and nonlinear activations), significantly reducing redundant computations. Experimental results on both synthetic and real-world datasets demonstrate the promising performance of NeuMatC, exemplified by over $3\times$ speedup in parametric inversion and $10\times$ speedup in parametric SVD compared to the widely used NumPy baseline in wireless communication, while maintaining acceptable accuracy.

cs.CV↗

arXiv2025

Classical Algorithms for Hamiltonian Dynamics Mean Value and Guided Local Hamiltonian Problem

The efficient simulation of quantum dynamics and ground states is a central challenge in physics and a key frontier for quantum advantage. While short-time evolution in one-dimensional systems can often be simulated classically, extending this to higher dimensions remains difficult. Here, we introduce an efficient classical algorithm for simulating the short-time dynamics of arbitrary local quantum systems. For any local Hamiltonian $H$ and constant evolution time $t$, our method estimates expectation values of the form $\langleψ|e^{iHt}Oe^{-iHt}|ψ\rangle$ for global Pauli observables $O$ and stabilizer states $|ψ\rangle$, with high precision and exponentially small failure probability. Furthermore, we present a classical dequantization of a tailored quantum algorithm that efficiently solves the guided local Hamiltonian (GLH) problem to constant additive error - previously considered classically hard and hence a promising candidate for quantum computational advantage. These results reveal unexpected classical tractability in constant-time quantum dynamics and fundamental connections between Hamiltonian dynamics mean value and the GLH problem. Our work refines the boundary between classical and quantum computational power, identifying sharper criteria for regimes where quantum advantage may genuinely emerge.

quant-ph↗