arXiv subjects

Chong Chen

Publications and source records attributed to Chong Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval

Determining which legal cases are relevant to a given query involves navigating lengthy texts and applying nuanced legal reasoning. Traditionally, this task has demanded significant time and domain expertise to identify key Legal Facts and reach sound juridical conclusions. In addition, existing data with legal case similarities often lack interpretability, making it difficult to understand the rationale behind relevance judgments. With the growing capabilities of large language models (LLMs), researchers have begun investigating their potential in this domain. Nonetheless, the method of employing a general large language model for reliable relevance judgments in legal case retrieval remains largely unexplored. To address this gap in research, we propose a novel few-shot approach where LLMs assist in generating expert-aligned interpretable relevance judgments. The proposed approach decomposes the judgment process into several stages, mimicking the workflow of human annotators and allowing for the flexible incorporation of expert reasoning to improve the accuracy of relevance judgments. Importantly, it also ensures interpretable data labeling, providing transparency and clarity in the relevance assessment process. Through a comparison of relevance judgments made by LLMs and human experts, we empirically demonstrate that the proposed approach can yield reliable and valid relevance assessments. Furthermore, we demonstrate that with minimal expert supervision, our approach enables a large language model to acquire case analysis expertise and subsequently transfers this ability to a smaller model via annotation-based knowledge distillation.

cs.AI↗

arXiv2025

SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models

Vision-Language Models (VLMs) have recently emerged, demonstrating remarkable vision-understanding capabilities. However, training these models requires large-scale datasets, which brings challenges related to efficiency, effectiveness, and quality of web data. In this paper, we introduce SynthVLM, a new data synthesis and curation method for generating image-caption pairs. Unlike traditional methods, where captions are generated from images, SynthVLM utilizes advanced diffusion models and high-quality captions to synthesize and select images from text captions, thereby creating precisely aligned image-text pairs. We further introduce SynthVLM-100K, a high-quality dataset consisting of 100K curated and synthesized image-caption pairs. In both model and human evaluations, SynthVLM-100K outperforms traditional real-world datasets. Leveraging this dataset, we develop a new family of multimodal large language models (MLLMs), SynthVLM-7B and SynthVLM-13B, which achieve state-of-the-art (SOTA) performance on various vision question-answering (VQA) tasks. Notably, our models outperform LLaVA across most metrics with only 18\% pretrain data. Furthermore, SynthVLM-7B and SynthVLM-13B attain SOTA performance on the MMLU benchmark, demonstrating that the high-quality SynthVLM-100K dataset preserves language abilities.

cs.CV↗

arXiv2025

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation

Current research on Multimodal Retrieval-Augmented Generation (MRAG) enables diverse multimodal inputs but remains limited to single-modality outputs, restricting expressive capacity and practical utility. In contrast, real-world applications often demand both multimodal inputs and multimodal outputs for effective communication and grounded reasoning. Motivated by the recent success of Reinforcement Learning (RL) in complex reasoning tasks for Large Language Models (LLMs), we adopt RL as a principled and effective paradigm to address the multi-step, outcome-driven challenges inherent in multimodal output generation. Here, we introduce M2IO-R1, a novel framework for Multimodal Retrieval-Augmented Multimodal Generation (MRAMG) that supports both multimodal inputs and outputs. Central to our framework is an RL-based inserter, Inserter-R1-3B, trained with Group Relative Policy Optimization to guide image selection and placement in a controllable and semantically aligned manner. Empirical results show that our lightweight 3B inserter achieves strong reasoning capabilities with significantly reduced latency, outperforming baselines in both quality and efficiency.

cs.IR↗

arXiv2025

AFIRE: Accurate and Fast Image Reconstruction Algorithm for Geometric-inconsistent Multispectral CT

For nonlinear multispectral computed tomography (CT), accurate and fast image reconstruction is challenging when the scanning geometries under different X-ray energy spectra are inconsistent or mismatched. Motivated by this, we propose an Accurate and Fast Image REconstruction (AFIRE) algorithm to address such problems in the case of mildly full scan. From the continuous (resp. discrete) setting, we discover that the derivative operator (gradient) of the involved nonlinear mapping at some special points, for example, at zero, can be represented as a composition (block multiplication) of a diagonal operator (matrix) composed of X-ray transforms (projection matrices) and a very small-scale matrix. Based on these insights, the AFIRE algorithm is proposed by leveraging the simplified Newton method. Under proper conditions, we establish the convergence theory of the proposed algorithm. Furthermore, numerical experiments are also carried out to verify that the proposed algorithm can accurately and effectively reconstruct the basis images in completely geometric-inconsistent dual-energy CT with noiseless and noisy projection data. Particularly, the proposed algorithm significantly outperforms some state-of-the-art methods in terms of accuracy and efficiency. Finally, the flexibility and extensibility of the proposed algorithm are also demonstrated.

math.NA↗

arXiv2025

CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification

Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costly to acquire. A credible solution is to explore additional labeled graphs to enhance unsupervised learning on the target domain. However, how to apply GNNs to domain adaptation remains unsolved owing to the insufficient exploration of graph topology and the significant domain discrepancy. In this paper, we propose Coupled Contrastive Graph Representation Learning (CoCo), which extracts the topological information from coupled learning branches and reduces the domain discrepancy with coupled contrastive learning. CoCo contains a graph convolutional network branch and a hierarchical graph kernel network branch, which explore graph topology in implicit and explicit manners. Besides, we incorporate coupled branches into a holistic multi-view contrastive learning framework, which not only incorporates graph representations learned from complementary views for enhanced understanding, but also encourages the similarity between cross-domain example pairs with the same semantics for domain alignment. Extensive experiments on popular datasets show that our CoCo outperforms these competing baselines in different settings generally.

cs.LG↗

arXiv2025

Multi-dynamic deep image prior for cardiac MRI

Cardiovascular magnetic resonance imaging is a powerful diagnostic tool for assessing cardiac structure and function. However, traditional breath-held imaging protocols pose challenges for patients with arrhythmias or limited breath-holding capacity. This work aims to overcome these limitations by developing a reconstruction framework that enables high-quality imaging in free-breathing conditions for various dynamic cardiac MRI protocols. Multi-Dynamic Deep Image Prior (M-DIP), a novel unsupervised reconstruction framework for accelerated real-time cardiac MRI, is introduced. To capture contrast or content variation, M-DIP first employs a spatial dictionary to synthesize a time-dependent intermediate image. Then, this intermediate image is further refined using time-dependent deformation fields that model cardiac and respiratory motion. Unlike prior DIP-based methods, M-DIP simultaneously captures physiological motion and frame-to-frame content variations, making it applicable to a wide range of dynamic applications. We validate M-DIP using simulated MRXCAT cine phantom data as well as free-breathing real-time cine, single-shot late gadolinium enhancement (LGE), and first-pass perfusion data from clinical patients. Comparative analyses against state-of-the-art supervised and unsupervised approaches demonstrate M-DIP's performance and versatility. M-DIP achieved better image quality metrics on phantom data, higher reader scores on in-vivo cine and LGE data, and comparable scores on in-vivo perfusion data relative to another DIP-based approach. M-DIP enables high-quality reconstructions of real-time free-breathing cardiac MRI without requiring external training data. Its ability to model physiological motion and content variations makes it a promising approach for various dynamic imaging applications.

physics.med-ph↗

arXiv2025

Near Data Processing in Taurus Database

Huawei's cloud-native database system GaussDB for MySQL (also known as Taurus) stores data in a separate storage layer consisting of a pool of storage servers. Each server has considerable compute power making it possible to push data reduction operations (selection, projection, and aggregation) close to storage. This paper describes the design and implementation of near data processing (NDP) in Taurus. NDP has several benefits: it reduces the amount of data shipped over the network; frees up CPU capacity in the compute layer; and reduces query run time, thereby enabling higher system throughput. Experiments with the TPCH benchmark (100 GB) showed that 18 out of 22 queries benefited from NDP; data shipped was reduced by 63 percent; and CPU time by 50 percent. On Q15 the impact was even higher: data shipped was reduced by 98 percent; CPU time by 91 percent; and run time by 80 percent.

cs.DB↗

arXiv2025

Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search

Text-to-SQL, which enables natural language interaction with databases, serves as a pivotal method across diverse industries. With new, more powerful large language models (LLMs) emerging every few months, fine-tuning has become incredibly costly, labor-intensive, and error-prone. As an alternative, zero-shot Text-to-SQL, which leverages the growing knowledge and reasoning capabilities encoded in LLMs without task-specific fine-tuning, presents a promising and more challenging direction. To address this challenge, we propose Alpha-SQL, a novel approach that leverages a Monte Carlo Tree Search (MCTS) framework to iteratively infer SQL construction actions based on partial reasoning states. To enhance the framework's reasoning capabilities, we introduce LLM-as-Action-Model to dynamically generate SQL construction actions during the MCTS process, steering the search toward more promising SQL queries. Moreover, Alpha-SQL employs a self-supervised reward function to evaluate the quality of candidate SQL queries, ensuring more accurate and efficient query generation. Experimental results show that Alpha-SQL achieves 69.7% execution accuracy on the BIRD development set, using a 32B open-source LLM without fine-tuning. Alpha-SQL outperforms the best previous zero-shot approach based on GPT-4o by 2.5% on the BIRD development set.

cs.DB↗

arXiv2025

An unsupervised method for MRI recovery: Deep image prior with structured sparsity

Objective: To propose and validate an unsupervised MRI reconstruction method that does not require fully sampled k-space data. Materials and Methods: The proposed method, deep image prior with structured sparsity (DISCUS), extends the deep image prior (DIP) by introducing group sparsity to frame-specific code vectors, enabling the discovery of a low-dimensional manifold for capturing temporal variations. \discus was validated using four studies: (I) simulation of a dynamic Shepp-Logan phantom to demonstrate its manifold discovery capabilities, (II) comparison with compressed sensing and DIP-based methods using simulated single-shot late gadolinium enhancement (LGE) image series from six distinct digital cardiac phantoms in terms of normalized mean square error (NMSE) and structural similarity index measure (SSIM), (III) evaluation on retrospectively undersampled single-shot LGE data from eight patients, and (IV) evaluation on prospectively undersampled single-shot LGE data from eight patients, assessed via blind scoring from two expert readers. Results: DISCUS outperformed competing methods, demonstrating superior reconstruction quality in terms of NMSE and SSIM (Studies I--III) and expert reader scoring (Study IV). Discussion: An unsupervised image reconstruction method is presented and validated on simulated and measured data. These developments can benefit applications where acquiring fully sampled data is challenging.

eess.IV↗

arXiv2025

Groupwise Image Registration with Edge-Based Loss for Low-SNR Cardiac MRI

Purpose: To perform image registration and averaging of multiple free-breathing single-shot cardiac images, where the individual images may have a low signal-to-noise ratio (SNR). Methods: To address low SNR encountered in single-shot imaging, especially at low field strengths, we propose a fast deep learning (DL)-based image registration method, called Averaging Morph with Edge Detection (AiM-ED). AiM-ED jointly registers multiple noisy source images to a noisy target image and utilizes a noise-robust pre-trained edge detector to define the training loss. We validate AiM-ED using synthetic late gadolinium enhanced (LGE) images from the MR extended cardiac-torso (MRXCAT) phantom and free-breathing single-shot LGE images from healthy subjects (24 slices) and patients (5 slices) under various levels of added noise. Additionally, we demonstrate the clinical feasibility of AiM-ED by applying it to data from patients (6 slices) scanned on a 0.55T scanner. Results: Compared to a traditional energy-minimization-based image registration method and DL-based VoxelMorph, images registered using AiM-ED exhibit higher values of recovery SNR and three perceptual image quality metrics. An ablation study shows the benefit of both jointly processing multiple source images and using an edge map in AiM-ED. Conclusion: For single-shot LGE imaging, AiM-ED outperforms existing image registration methods in terms of image quality. With fast inference, minimal training data requirements, and robust performance at various noise levels, AiM-ED has the potential to benefit single-shot CMR applications.

eess.IV↗

arXiv2025

Including Bloom Filters in Bottom-up Optimization

Bloom filters are used in query processing to perform early data reduction and improve query performance. The optimal query plan may be different when Bloom filters are used, indicating the need for Bloom filter-aware query optimization. To date, Bloom filter-aware query optimization has only been incorporated in a top-down query optimizer and limited to snowflake queries. In this paper, we show how Bloom filters can be incorporated in a bottom-up cost-based query optimizer. We highlight the challenges in limiting optimizer search space expansion, and offer an efficient solution. We show that including Bloom filters in cost-based optimization can lead to better join orders with effective predicate transfer between operators. On a 100 GB instance of the TPC-H database, our approach achieved a 32.8% further reduction in latency for queries involving Bloom filters, compared to the traditional approach of adding Bloom filters in a separate post-optimization step. Our method applies to all query types, and we provide several heuristics to balance limited increases in optimization time against improved query latency.

cs.DB↗

arXiv2025

Deep Cut-informed Graph Embedding and Clustering

Graph clustering aims to divide the graph into different clusters. The recently emerging deep graph clustering approaches are largely built on graph neural networks (GNN). However, GNN is designed for general graph encoding and there is a common issue of representation collapse in existing GNN-based deep graph clustering algorithms. We attribute two main reasons for such issues: (i) the inductive bias of GNN models: GNNs tend to generate similar representations for proximal nodes. Since graphs often contain a non-negligible amount of inter-cluster links, the bias results in error message passing and leads to biased clustering; (ii) the clustering guided loss function: most traditional approaches strive to make all samples closer to pre-learned cluster centers, which causes a degenerate solution assigning all data points to a single label thus making all samples similar and less discriminative. To address these challenges, we investigate graph clustering from a graph cut perspective and propose an innovative and non-GNN-based Deep Cut-informed Graph embedding and Clustering framework, namely DCGC. This framework includes two modules: (i) cut-informed graph encoding; (ii) self-supervised graph clustering via optimal transport. For the encoding module, we derive a cut-informed graph embedding objective to fuse graph structure and attributes by minimizing their joint normalized cut. For the clustering module, we utilize the optimal transport theory to obtain the clustering assignments, which can balance the guidance of "proximity to the pre-learned cluster center". With the above two tailored designs, DCGC is more suitable for the graph clustering task, which can effectively alleviate the problem of representation collapse and achieve better performance. We conduct extensive experiments to demonstrate that our method is simple but effective compared with benchmarks.

cs.LG↗

arXiv2025

Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation

Cross-domain Sequential Recommendation (CDSR) aims to extract the preference from the user's historical interactions across various domains. Despite some progress in CDSR, two problems set the barrier for further advancements, i.e., overlap dilemma and transition complexity. The former means existing CDSR methods severely rely on users who own interactions on all domains to learn cross-domain item relationships, compromising the practicability. The latter refers to the difficulties in learning the complex transition patterns from the mixed behavior sequences. With powerful representation and reasoning abilities, Large Language Models (LLMs) are promising to address these two problems by bridging the items and capturing the user's preferences from a semantic view. Therefore, we propose an LLMs Enhanced Cross-domain Sequential Recommendation model (LLM4CDSR). To obtain the semantic item relationships, we first propose an LLM-based unified representation module to represent items. Then, a trainable adapter with contrastive regularization is designed to adapt the CDSR task. Besides, a hierarchical LLMs profiling module is designed to summarize user cross-domain preferences. Finally, these two modules are integrated into the proposed tri-thread framework to derive recommendations. We have conducted extensive experiments on three public cross-domain datasets, validating the effectiveness of LLM4CDSR. We have released the code online.

cs.IR↗

arXiv2025

MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation

Recent advances in Retrieval-Augmented Generation (RAG) have significantly improved response accuracy and relevance by incorporating external knowledge into Large Language Models (LLMs). However, existing RAG methods primarily focus on generating text-only answers, even in Multimodal Retrieval-Augmented Generation (MRAG) scenarios, where multimodal elements are retrieved to assist in generating text answers. To address this, we introduce the Multimodal Retrieval-Augmented Multimodal Generation (MRAMG) task, in which we aim to generate multimodal answers that combine both text and images, fully leveraging the multimodal data within a corpus. Despite growing attention to this challenging task, a notable lack of a comprehensive benchmark persists for effectively evaluating its performance. To bridge this gap, we provide MRAMG-Bench, a meticulously curated, human-annotated benchmark comprising 4,346 documents, 14,190 images, and 4,800 QA pairs, distributed across six distinct datasets and spanning three domains: Web, Academia, and Lifestyle. The datasets incorporate diverse difficulty levels and complex multi-image scenarios, providing a robust foundation for evaluating the MRAMG task. To facilitate rigorous evaluation, MRAMG-Bench incorporates a comprehensive suite of both statistical and LLM-based metrics, enabling a thorough analysis of the performance of generative models in the MRAMG task. Additionally, we propose an efficient and flexible multimodal answer generation framework that can leverage LLMs/MLLMs to generate multimodal responses. Our datasets and complete evaluation results for 11 popular generative models are available at https://github.com/MRAMG-Bench/MRAMG.

cs.LG↗

arXiv2025

Accelerated Real-time Cine and Flow under In-magnet Staged Exercise

Background: Cardiovascular magnetic resonance imaging (CMR) is a well established imaging tool for diagnosing and managing cardiac conditions. The integration of exercise stress with CMR (ExCMR) can enhance its diagnostic capacity. Despite recent advances in CMR technology, quantitative ExCMR during exercise remains technically challenging due to motion artifacts and limited spatial and temporal resolution. Methods: This study investigated the feasibility of biventricular functional and hemodynamic assessment using real-time (RT) ExCMR during a staged exercise protocol in 24 healthy volunteers. We employed high acceleration rates and applied a coil reweighting technique to minimize motion blurring and artifacts. We further applied a beat-selection technique that identified beats from the endexpiratory phase to minimize the impact of respiration-induced through-plane motion on cardiac function quantification. Additionally, results from six patients were presented to demonstrate clinical feasibility. Results: Our findings indicated a consistent decrease in end-systolic volume and stable end-diastolic volume across exercise intensities, leading to increased stroke volume and ejection fraction. The selection of end-expiratory beats modestly enhanced the repeatability of cardiac function parameters, as shown by scan-rescan tests in nine volunteers. High scores from a blinded image quality assessment indicated that coil reweighting effectively minimized motion artifacts. Conclusions: This study demonstrated the feasibility of RT ExCMR with inmagnet exercise in healthy subjects and patients. Our results indicate that high acceleration rates, coil reweighting, and selection of respiratory phase-specific heartbeats enhance image quality and repeatability of quantitative RT ExCMR.

eess.SP↗

arXiv2025

A Survey of Multimodal Retrieval-Augmented Generation

Multimodal Retrieval-Augmented Generation (MRAG) enhances large language models (LLMs) by integrating multimodal data (text, images, videos) into retrieval and generation processes, overcoming the limitations of text-only Retrieval-Augmented Generation (RAG). While RAG improves response accuracy by incorporating external textual knowledge, MRAG extends this framework to include multimodal retrieval and generation, leveraging contextual information from diverse data types. This approach reduces hallucinations and enhances question-answering systems by grounding responses in factual, multimodal knowledge. Recent studies show MRAG outperforms traditional RAG, especially in scenarios requiring both visual and textual understanding. This survey reviews MRAG's essential components, datasets, evaluation methods, and limitations, providing insights into its construction and improvement. It also identifies challenges and future research directions, highlighting MRAG's potential to revolutionize multimodal information retrieval and generation. By offering a comprehensive perspective, this work encourages further exploration into this promising paradigm.

cs.IR↗

arXiv2025

Large Language Model Enhanced Recommender Systems: A Survey

Large Language Model (LLM) has transformative potential in various domains, including recommender systems (RS). There have been a handful of research that focuses on empowering the RS by LLM. However, previous efforts mainly focus on LLM as RS, which may face the challenge of intolerant inference costs by LLM. Recently, the integration of LLM into RS, known as LLM-Enhanced Recommender Systems (LLMERS), has garnered significant interest due to its potential to address latency and memory constraints in real-world applications. This paper presents a comprehensive survey of the latest research efforts aimed at leveraging LLM to enhance RS capabilities. We identify a critical shift in the field with the move towards incorporating LLM into the online system, notably by avoiding their use during inference. Our survey categorizes the existing LLMERS approaches into three primary types based on the component of the RS model being augmented: Knowledge Enhancement, Interaction Enhancement, and Model Enhancement. We provide an in-depth analysis of each category, discussing the methodologies, challenges, and contributions of recent studies. Furthermore, we highlight several promising research directions that could further advance the field of LLMERS.

cs.IR↗

arXiv2025

PanguIR Technical Report for NTCIR-18 AEOLLM Task

As large language models (LLMs) gain widespread attention in both academia and industry, it becomes increasingly critical and challenging to effectively evaluate their capabilities. Existing evaluation methods can be broadly categorized into two types: manual evaluation and automatic evaluation. Manual evaluation, while comprehensive, is often costly and resource-intensive. Conversely, automatic evaluation offers greater scalability but is constrained by the limitations of its evaluation criteria (dominated by reference-based answers). To address these challenges, NTCIR-18 introduced the AEOLLM (Automatic Evaluation of LLMs) task, aiming to encourage reference-free evaluation methods that can overcome the limitations of existing approaches. In this paper, to enhance the evaluation performance of the AEOLLM task, we propose three key methods to improve the reference-free evaluation: 1) Multi-model Collaboration: Leveraging multiple LLMs to approximate human ratings across various subtasks; 2) Prompt Auto-optimization: Utilizing LLMs to iteratively refine the initial task prompts based on evaluation feedback from training samples; and 3) In-context Learning (ICL) Optimization: Based on the multi-task evaluation feedback, we train a specialized in-context example retrieval model, combined with a semantic relevance retrieval model, to jointly identify the most effective in-context learning examples. Experiments conducted on the final dataset demonstrate that our approach achieves superior performance on the AEOLLM task.

cs.CL↗