arXiv subjects

Jianwei Wang

Publications and source records attributed to Jianwei Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

High-Dimensional Quantum Photonics: Roadmap

The field of high-dimensional quantum photonics involves the use of multimode photonic degrees-of-freedom such as the spatial, temporal, or spectral structure of light to encode multi-level quantum states. Recent years have seen rapid progress in the development of methods to generate, manipulate, and distribute such quantum states of light and their use in a range of quantum technology applications that offer practical advantages over conventional qubit-based approaches. High-dimensional quantum states of light encoded in photonic time-bins, frequency-bins, transverse-spatial modes, waveguide paths, and temporal modes have enabled noise-robust fundamental tests of quantum mechanics, error-resilient and high-capacity quantum communication protocols, andas well as efficient approaches for quantum information processing, to name just a few examples. However, research in this field has progressed fairly independently, with little exchange across different photonic degrees-of-freedom or between experiment and theory and no comprehensive comparison between degrees-of-freedom. This roadmap aims to bridge this gap by surveying progress in each area and identifying shared challenges and opportunities that cut across two or more photonic degrees-of-freedoms. We review early work and state-of-the-art experimental techniques under development for high-dimensional quantum states encoded in single and entangled photons, as well as theoretical tools for their measurement and certification. We outline the main outstanding challenges for theory and each experimental degree-of-freedom, identifying promising future directions of research that may enable these to be overcome. We end by discussing interconnections and shared challenges centered around their distribution, measurement, and manipulation, with a view towards their integration into next-generation quantum technology platforms and applications.

quant-ph↗

arXiv2026

Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory

Recent advances in large language models have driven the emergence of intelligent agents operating in open-world, multimodal environments. To support long-term reasoning, such agents are typically equipped with external memory systems. However, most existing multimodal agent memories rely primarily on neural representations and vector-based retrieval, which are well-suited for inductive, intuitive reasoning but fundamentally limited in supporting analytical, deductive reasoning critical for real-world decision making. To address this limitation, we propose NS-Mem, a long-term neuro-symbolic memory framework designed to advance multimodal agent reasoning by integrating neural memory with explicit symbolic structures and rules. Specifically, NS-Mem is operated around three core components of a memory system: (1) a three-layer memory architecture that consists episodic layer, semantic layer and logic rule layer, (2) a memory construction and maintenance mechanism implemented by SK-Gen that automatically consolidates structured knowledge from accumulated multimodal experiences and incrementally updates both neural representations and symbolic rules, and (3) a hybrid memory retrieval mechanism that combines similarity-based search with deterministic symbolic query functions to support structured reasoning. Experiments on real-world multimodal reasoning benchmarks demonstrate that Neural-Symbolic Memory achieves an average 4.35% improvement in overall reasoning accuracy over pure neural memory systems, with gains of up to 12.5% on constrained reasoning queries, validating the effectiveness of NS-Mem.

cs.AI↗

arXiv2026

TrustResearcher: Automating Knowledge-Grounded and Transparent Research Ideation with Multi-Agent Collaboration

Agentic systems have recently emerged as a promising tool to automate literature-based ideation. However, current systems often remain black-box, with limited transparency or control for researchers. Our work introduces TrustResearcher, a multi-agent demo system for knowledge-grounded and transparent ideation. Specifically, TrustResearcher integrates meticulously designed four stages into a unified framework: (A) Structured Knowledge Curation, (B) Diversified Idea Generation, (C) Multi-stage Idea Selection, and (D) Expert Panel Review and Synthesis. Different from prior pipelines, our system not only exposes intermediate reasoning states, execution logs, and configurable agents for inspections, but also enables diverse and evidence-aligned idea generation. Our design is also domain-agnostic, where the same pipeline can be instantiated in any scientific field. As an illustrative case, we demonstrate TrustResearcher on a graph-mining scenario (k-truss breaking problem), where it generates distinct, plausible candidates with evidence and critiques. A live demo and source code are available at https://github.com/valleysprings/TrustResearcher

cs.MA↗

arXiv2026

RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior

Large Language Models (LLMs) with long chain-of-thought (CoT) capability, termed Reasoning Models, demonstrate superior intricate problem-solving abilities through multi-step long CoT reasoning. To create a dual-capability model with long CoT capability and domain-specific knowledge without substantial computational and data costs, model merging emerges as a highly resource-efficient method. However, significant challenges lie in merging domain-specific LLMs with long CoT ones since nowadays merging methods suffer from reasoning capability degradation, even gibberish output and output collapse. To overcome this, we introduce RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior, a novel merging framework designed to integrate domain-specific LLMs with long CoT capability, meanwhile maintaining model performance in the original domain. Treating reasoning model weights as foundational prior, our method utilizes a reasoning capability indicator to preserve core long CoT capability model weights while selectively merging essential domain-specific weights. We conducted extensive experiments on Qwen2.5-7B, Llama3.1-8B, and Qwen2.5-1.5B models in BioMedicine and Finance domains. Our results show that RCP-Merging successfully merges a reasoning model with domain-specific ones, improving domain task performance by 9.5% and 9.2% over state-of-the-art methods, without significantly harming the original long CoT reasoning capability.

cs.CL↗

arXiv2026

HyperJoin: LLM-augmented Hypergraph Link Prediction for Joinable Table Discovery

As a pivotal task in data lake management, joinable table discovery has attracted widespread interest. While existing language model-based methods achieve remarkable performance by combining offline column representation learning with online ranking, their design insufficiently accounts for the underlying structural interactions: (1) offline, they directly model tables into isolated or pairwise columns, thereby struggling to capture the rich inter-table and intra-table structural information; and (2) online, they rank candidate columns based solely on query-candidate similarity, ignoring the mutual interactions among the candidates, leading to incoherent result sets. To address these limitations, we propose HyperJoin, a large language model (LLM)-augmented Hypergraph framework for Joinable table discovery. Specifically, we first construct a hypergraph to model tables using both the intra-table hyperedges and the LLM-augmented inter-table hyperedges. Consequently, the task of joinable table discovery is formulated as link prediction on this constructed hypergraph. We then design HIN, a Hierarchical Interaction Network that learns expressive column representations through bidirectional message passing over columns and hyperedges. To strengthen coherence and internal consistency in the result columns, we cast online ranking as a coherence-aware top-k column selection problem. We then introduce a reranking module that leverages a maximum spanning tree algorithm to prune noisy connections and maximize coherence. Experiments demonstrate the superiority of HyperJoin, achieving average improvements of 21.4% (Precision@15) and 17.2% (Recall@15) over the best baseline.

cs.CL↗

arXiv2025

A power-in-bucket model enabled designs of nanostructure-enhanced waveguides for highly efficient wide-angle light couplings

Well-designed nanostructures on fiber facets can boost wide-angle light coupling and thus gain considerable attention because of the potential for intensive applications. However, previous theories commonly concentrate on the configurations of the bare waveguide, lacking full consideration of structure-assisted couplings. Here, a power-in-bucket (PIB) model is introduced to explore the coupling behavior of structure-modified waveguides. The analytical model investigates two representative coupling scenarios,including Gaussian beam and plane wave excitation. The PIB-computed coefficient η enhancements agree well with the experimental values, especially for the multiple-mode fibers under large-angle illuminations. Using PIB to optimize the beam-fiber parameters, we show that at the incidence angle of 37 degree, η could increase from 0.3320 to 0.5102 by the identical ring gratings. Overall, the proposed model provides a useful account of the mechanism of grating-aided light couplings. These findings would be of great help in designing structure-enhanced probes for wide-angle broadband light collection applications.

physics.optics↗

arXiv2025

DINO-BOLDNet: A DINOv3-Guided Multi-Slice Attention Network for T1-to-BOLD Generation

Generating BOLD images from T1w images offers a promising solution for recovering missing BOLD information and enabling downstream tasks when BOLD images are corrupted or unavailable. Motivated by this, we propose DINO-BOLDNet, a DINOv3-guided multi-slice attention framework that integrates a frozen self-supervised DINOv3 encoder with a lightweight trainable decoder. The model uses DINOv3 to extract within-slice structural representations, and a separate slice-attention module to fuse contextual information across neighboring slices. A multi-scale generation decoder then restores fine-grained functional contrast, while a DINO-based perceptual loss encourages structural and textural consistency between predictions and ground-truth BOLD in the transformer feature space. Experiments on a clinical dataset of 248 subjects show that DINO-BOLDNet surpasses a conditional GAN baseline in both PSNR and MS-SSIM. To our knowledge, this is the first framework capable of generating mean BOLD images directly from T1w images, highlighting the potential of self-supervised transformer guidance for structural-to-functional mapping.

cs.CV↗

arXiv2025

High-dimensional Path-Encoded Entanglement Distribution Between Photonic Chips Enabled by Multimode Phase Stabilisation

The reliable distribution of high-dimensional entangled quantum states, an important resource in quantum technologies, through optical fibre networks is challenging due to the need to maintain coherence across multiple modes. Here we demonstrate the distribution of four-dimensional path-encoded entangled quantum states between photonic chips, enabled by a novel multimode phase stabilisation algorithm. The algorithm utilises the reconfigurability of the integrated photonic circuits to complete one iteration of phase stabilisation in just two measurement rounds for an arbitrary number of modes, and requires no additional hardware to the quantum measurements it enables. As a result, we are able to perform complete quantum state tomography across two chips using the minimum number of local projective measurements to verify the fidelity of the distributed entangled state to be 86% (compared to 8.1% without the phase stabilisation) with an entanglement entropy of 0.995+/-0.002.

quant-ph↗

arXiv2025

Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications

Large Language Models (LLMs) have achieved remarkable success in natural language processing through strong semantic understanding and generation. However, their black-box nature limits structured and multi-hop reasoning. In contrast, Text-Attributed Graphs (TAGs) provide explicit relational structures enriched with textual context, yet often lack semantic depth. Recent research shows that combining LLMs and TAGs yields complementary benefits: enhancing TAG representation learning and improving the reasoning and interpretability of LLMs. This survey provides the first systematic review of LLM--TAG integration from an orchestration perspective. We introduce a novel taxonomy covering two fundamental directions: LLM for TAG, where LLMs enrich graph-based tasks, and TAG for LLM, where structured graphs improve LLM reasoning. We categorize orchestration strategies into sequential, parallel, and multi-module frameworks, and discuss advances in TAG-specific pretraining, prompting, and parameter-efficient fine-tuning. Beyond methodology, we summarize empirical insights, curate available datasets, and highlight diverse applications across recommendation systems, biomedical analysis, and knowledge-intensive question answering. Finally, we outline open challenges and promising research directions, aiming to guide future work at the intersection of language and graph learning.

cs.CL↗

arXiv2025

Optimal scheme for distributed quantum metrology

Optimal strategies for local quantum metrology -- including the preparation of optimal probe states, implementation of optimal control and measurement strategies, are well established. However, for distributed quantum metrology, where the goal is to estimate global properties of multiple spatially distributed parameters, the optimal scheme -- particularly the role of optimal control -- remains poorly understood. In this work, we address this challenge by developing optimal schemes for distributed quantum metrology that characterize the ultimate precision limits in distributed systems. We derive the optimal probe state, optimal control protocols, and measurement strategies in estimating a linear combination of $N$ independent unknown parameters coupled to $d$ networked sensors. Crucially, we prove that the optimal control operations can be implemented locally on each sensor, eliminating the need for non-local control operations across distant nodes. This result significantly reduces the complexity of implementing optimal strategies in distributed quantum metrology. To demonstrate the power of our framework, we apply it to several key scenarios.

quant-ph↗

arXiv2025

RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis

The success of large language models (LLMs) has attracted many individuals to fine-tune them for domain-specific tasks by uploading their data. However, in sensitive areas like healthcare and finance, privacy concerns often arise. One promising solution is to generate synthetic data with Differential Privacy (DP) guarantees to replace private data. However, these synthetic data contain significant flawed data, which are considered as noise. Existing solutions typically rely on naive filtering by comparing ROUGE-L scores or embedding similarities, which are ineffective in addressing the noise. To address this issue, we propose \textit{RewardDS}, a novel privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation. Our \textit{RewardDS} introduces two key modules, Reward Guided Filtering and Self-Optimizing Refinement, to both filter and refine the synthetic data, effectively mitigating the noise. Extensive experiments across medical, financial, and code generation domains demonstrate the effectiveness of our method.

cs.CR↗

arXiv2025

Empowering Tabular Data Preparation with Language Models: Why and How?

Data preparation is a critical step in enhancing the usability of tabular data and thus boosts downstream data-driven tasks. Traditional methods often face challenges in capturing the intricate relationships within tables and adapting to the tasks involved. Recent advances in Language Models (LMs), especially in Large Language Models (LLMs), offer new opportunities to automate and support tabular data preparation. However, why LMs suit tabular data preparation (i.e., how their capabilities match task demands) and how to use them effectively across phases still remain to be systematically explored. In this survey, we systematically analyze the role of LMs in enhancing tabular data preparation processes, focusing on four core phases: data acquisition, integration, cleaning, and transformation. For each phase, we present an integrated analysis of how LMs can be combined with other components for different preparation tasks, highlight key advancements, and outline prospective pipelines.

cs.AI↗

arXiv2025

SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought

While Chain-of-Thought (CoT) reasoning improves model performance, it incurs significant time costs due to the generation of discrete CoT tokens (DCoT). Continuous CoT (CCoT) offers a more efficient alternative, but existing CCoT methods are hampered by indirect fine-tuning, limited alignment, or inconsistent targets. To overcome these limitations, we propose \textit{SynAdapt}, an innovative efficient reasoning framework. Specifically, \textit{SynAdapt} generates the synthetic CCoT to serve as a precise and effective alignment target for LLMs. This synthetic CCoT explicitly guides the LLM to learn CCoT and derive accurate answers directly. Furthermore, relying solely on CCoT is insufficient for solving hard questions. To address this, \textit{SynAdapt} integrates a difficulty classifier that leverages both question context and CCoT to identify hard questions. CCoT can effectively help identify hard questions after some brief reasoning. We then adaptively prompt the LLM to re-think these hard questions for improved performance. Extensive experimental results across various benchmarks from different difficulty levels strongly demonstrate the effectiveness of our method, achieving the best accuracy-efficiency trade-off.

cs.CL↗

arXiv2025

Universal Quantum Computational Spectroscopy on a Quantum Chip

Spectroscopy underpins modern scientific discovery across diverse disciplines. While experimental spectroscopy probes material properties through scattering or radiation measurements, computational spectroscopy combines theoretical models with experimental data to predict spectral properties, essential for advancements in physics, chemistry, and materials science. However, quantum systems present unique challenges for computational spectroscopy due to their inherent complexity, and current quantum algorithms remain largely limited to static and closed quantum systems. Here, we present and demonstrate a universal quantum computational spectroscopy framework that lifts these limitations. Through leveraging coherently controlled quantum dynamics, our method efficiently reconstructs the spectral information for both closed and open systems, furtherly for time-dependent driven systems. We experimentally validate this approach using a programmable silicon-photonic quantum processing chip, capable of high-fidelity time-evolution simulations. The versatility of our framework is demonstrated through spectroscopic computations for diverse quantum systems -- including spin systems, non-Hermitian systems, and quantum Floquet systems -- revealing novel phenomena such as parity-time symmetry breaking and topological holonomy that are inaccessible to conventional spectroscopy or quantum eigenstate algorithms. {Furthermore, systematic benchmarking of UQCS against existing quantum algorithms is numerically performed to demonstrate its unprecedented capabilities and superior performance. This work establishes a noise-robust and transformative paradigm for quantum spectral analysis.

quant-ph↗

arXiv2025

Correcting for finite statistics effects in a quantum steering experiment

Verifying entanglement between parties is essential for creating secure quantum communication. However, finite statistics can lead to false positive outcomes in any tests for entanglement. Here, we introduce a one-sided device-independent protocol that corrects for apparent signaling effects in experimental probability distributions, caused by statistical fluctuations and experimental imperfections. We use semidefinite programming to identify the optimal inequality, for our experimental probability distribution, without resource-intensive tomography. Our protocol is numerically and experimentally analysed in the context of random, misaligned measurements, correcting apparent signaling where necessary. Our results show a significantly higher probability of violation than existing state-of-the-art inequalities. This work demonstrates the power of semidefinite programming for entanglement verification and brings quantum networks closer to practical applications.

quant-ph↗

arXiv2025

ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimation

This paper studies optical flow estimation, a critical task in motion analysis with applications in autonomous navigation, action recognition, and film production. Traditional optical flow methods require consecutive frames, which are often unavailable due to limitations in data acquisition or real-world scene disruptions. Thus, single-frame optical flow estimation is emerging in the literature. However, existing single-frame approaches suffer from two major limitations: (1) they rely on labeled training data, making them task-specific, and (2) they produce deterministic predictions, failing to capture motion uncertainty. To overcome these challenges, we propose ProbDiffFlow, a training-free framework that estimates optical flow distributions from a single image. Instead of directly predicting motion, ProbDiffFlow follows an estimation-by-synthesis paradigm: it first generates diverse plausible future frames using a diffusion-based model, then estimates motion from these synthesized samples using a pre-trained optical flow model, and finally aggregates the results into a probabilistic flow distribution. This design eliminates the need for task-specific training while capturing multiple plausible motions. Experiments on both synthetic and real-world datasets demonstrate that ProbDiffFlow achieves superior accuracy, diversity, and efficiency, outperforming existing single-image and two-frame baselines.

cs.CV↗

arXiv2025

Variational quantum algorithms with invariant probabilistic error cancellation on noisy quantum processors

In the noisy intermediate-scale quantum era, emerging classical-quantum hybrid optimization algorithms, such as variational quantum algorithms (VQAs), can leverage the unique characteristics of quantum devices to accelerate computations tailored to specific problems with shallow circuits. However, these algorithms encounter biases and iteration difficulties due to significant noise in quantum processors. These difficulties can only be partially addressed without error correction by optimizing hardware, reducing circuit complexity, or fitting and extrapolation. A compelling solution is applying probabilistic error cancellation (PEC), a quantum error mitigation technique that enables unbiased results without full error correction. Traditional PEC is challenging to apply in VQAs due to its variance amplification, contradicting iterative process assumptions. This paper proposes a novel noise-adaptable strategy that combines PEC with the quantum approximate optimization algorithm (QAOA). It is implemented through invariant sampling circuits (invariant-PEC, or IPEC) and substantially reduces iteration variance. This strategy marks the first successful integration of PEC and QAOA, resulting in efficient convergence. Moreover, we introduce adaptive partial PEC (APPEC), which modulates the error cancellation proportion of IPEC during iteration. We experimentally validated this technique on a superconducting quantum processor, cutting sampling cost by 90.1\%. Notably, we find that dynamic adjustments of error levels via APPEC can enhance escape from local minima and reduce sampling costs. These results open promising avenues for executing VQAs with large-scale, low-noise quantum circuits, paving the way for practical quantum computing advancements.

quant-ph↗

arXiv2025

LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements

Health, Safety, and Environment (HSE) compliance assessment demands dynamic real-time decision-making under complicated regulations and complex human-machine-environment interactions. While large language models (LLMs) hold significant potential for decision intelligence and contextual dialogue, their capacity for domain-specific knowledge in HSE and structured legal reasoning remains underexplored. We introduce HSE-Bench, the first benchmark dataset designed to evaluate the HSE compliance assessment capabilities of LLM. HSE-Bench comprises over 1,000 manually curated questions drawn from regulations, court cases, safety exams, and fieldwork videos, and integrates a reasoning flow based on Issue spotting, rule Recall, rule Application, and rule Conclusion (IRAC) to assess the holistic reasoning pipeline. We conduct extensive evaluations on different prompting strategies and more than 10 LLMs, including foundation models, reasoning models and multimodal vision models. The results show that, although current LLMs achieve good performance, their capabilities largely rely on semantic matching rather than principled reasoning grounded in the underlying HSE compliance context. Moreover, their native reasoning trace lacks the systematic legal reasoning required for rigorous HSE compliance assessment. To alleviate these, we propose a new prompting technique, Reasoning of Expert (RoE), which guides LLMs to simulate the reasoning process of different experts for compliance assessment and reach a more accurate unified decision. We hope our study highlights reasoning gaps in LLMs for HSE compliance and inspires further research on related tasks.

cs.CL↗