arXiv subjects

Chong Chen

Publications and source records attributed to Chong Chen.

At least 55 records · Page 3Linked to original sources

arXiv2026

HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization

Tabular data contains rich structural semantics and plays a crucial role in organizing and manipulating information. Recent methods employ Multi-modal Large Language Models (MLLMs) to address table-related tasks across various modalities of table representations. However, existing studies mainly focus on exploring the table understanding ability of MLLMs using unimodal representations, which limits further exploration of multi-modal representations to enable more effective table reasoning. To better capture structural semantics from the tabular data, this paper introduces the HybrId-modal Preference oPtimizatiOn (HIPPO) model, which represents tables using both text and image, optimizing MLLMs by learning more comprehensive table information from these multiple modalities. Specifically, HIPPO samples MLLM responses from hybrid-modal table representations and designs a modality-consistent sampling strategy to enhance response diversity and mitigate modality bias during Direct Preference Optimization (DPO) training. Experiments on table question answering and table fact verification tasks demonstrate the effectiveness of HIPPO, achieving a 4% improvement over various table reasoning models. Further analysis reveals that HIPPO not only enhances the table reasoning capability based on unimodal representations but also facilitates the extraction of complementary semantics across modalities. The code is available at https://github.com/NEUIR/HIPPO.

cs.CL↗

arXiv2026

Structures in higher-order quantum correlations due to non-spatial symmetries

Quantum nonlinear spectroscopy (QNS) via a quantum sensor can access $2^{n-1}$ types of $n$-th order contour-time-ordered correlations (CTOCs) arising from different orderings of quantum operators, while classical nonlinear spectroscopy can detect only one in each order. QNS and its classical counterpart have similar spatial symmetry properties, but they are expected to have characteristically different non-spatial symmetry properties since different orderings of operators can behave differently under non-spatial transformations (such as exchange of operators). Here, we investigate how higher-order correlations extracted by QNS are constrained by non-spatial symmetries, including particle-hole (C), time-reversal (T), chiral (S) symmetry, and time translation symmetry. We find that the generalized C-symmetry imposes special selection rules on QNS, and the generalized T- and S-symmetry relate CTOCs to out-of-time-order correlations (OTOCs). The time translation symmetry leads to a generalized fluctuation-dissipation theorem for the spectra of higher-order CTOCs and OTOCs. This work discloses deep structures in higher-order quantum correlations due to non-spatial symmetries and provides access to certain types of OTOCs that are not directly observable.

quant-ph↗

arXiv2026

M$^3$Searcher: Modular Multimodal Information Seeking Agency with Retrieval-Oriented Reasoning

Recent advances in DeepResearch-style agents have demonstrated strong capabilities in autonomous information acquisition and synthesize from real-world web environments. However, existing approaches remain fundamentally limited to text modality. Extending autonomous information-seeking agents to multimodal settings introduces critical challenges: the specialization-generalization trade-off that emerges when training models for multimodal tool-use at scale, and the severe scarcity of training data capturing complex, multi-step multimodal search trajectories. To address these challenges, we propose M$^3$Searcher, a modular multimodal information-seeking agent that explicitly decouples information acquisition from answer derivation. M$^3$Searcher is optimized with a retrieval-oriented multi-objective reward that jointly encourages factual accuracy, reasoning soundness, and retrieval fidelity. In addition, we develop MMSearchVQA, a multimodal multi-hop dataset to support retrieval centric RL training. Experimental results demonstrate that M$^3$Searcher outperforms existing approaches, exhibits strong transfer adaptability and effective reasoning in complex multimodal tasks.

cs.AI↗

arXiv2025

AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning

Recent studies have explored integrating Large Language Models (LLMs) with search engines to leverage both the LLMs' internal pre-trained knowledge and external information. Specially, reinforcement learning (RL) has emerged as a promising paradigm for enhancing LLM reasoning through multi-turn interactions with search engines. However, existing RL-based search agents rely on a single LLM to handle both search planning and question-answering (QA) tasks in an end-to-end manner, which limits their ability to optimize both capabilities simultaneously. In practice, sophisticated AI search systems often employ a large, frozen LLM (e.g., GPT-4, DeepSeek-R1) to ensure high-quality QA. Thus, a more effective and efficient approach is to utilize a small, trainable LLM dedicated to search planning. In this paper, we propose \textbf{AI-SearchPlanner}, a novel reinforcement learning framework designed to enhance the performance of frozen QA models by focusing on search planning. Specifically, our approach introduces three key innovations: 1) Decoupling the Architecture of the Search Planner and Generator, 2) Dual-Reward Alignment for Search Planning, and 3) Pareto Optimization of Planning Utility and Cost, to achieve the objectives. Extensive experiments on real-world datasets demonstrate that AI SearchPlanner outperforms existing RL-based search agents in both effectiveness and efficiency, while exhibiting strong generalization capabilities across diverse frozen QA models and data domains.

cs.AI↗

arXiv2025

Artificial electrostatic crystals: a new platform for creating correlated quantum states

The electronic properties of solids are determined by the crystal structure and interactions between electrons, giving rise to a variety of collective phenomena including superconductivity, strange metals and correlated insulators. The mechanisms underpinning many of these collective phenomena remain unknown, driving interest in creating artificial crystals which replicate the system of interest while allowing precise control of key parameters. Here we demonstrate the formation of highly tunable artificial crystals by superimposing a periodic electrostatic potential on the 2D electron gas in an ultra-shallow (25 nm deep) GaAs quantum well. The 100 nm period artificial crystal is identified by the formation of a new bandstructure, different from the original cubic crystal and specific to the artificial triangular lattice: transport measurements show the Hall coefficient changing sign as the chemical potential sweeps through the artificial bands. Uniquely, the artificial bandstructure can be continuously tuned to form linear graphene-like and flat kagome-like bands in a single device. A strong insulating state is observed at half filling of the kagome flat band, which is not expected in the absence of strong interactions. This state, unique to the kagome lattice, is consistent with a loop-current Wigner insulator, which arises from long-range Coulomb interaction and delocalised electrons between neighbouring empty sites. The ability to continuously tune the bandstructure and access flat bands through electrical gating within a single device opens a new route to studying collective quantum states.

cond-mat.mes-hall↗

arXiv2025

A multi-dynamic low-rank deep image prior (ML-DIP) for 3D real-time cardiovascular MRI

Purpose: To develop a reconstruction framework for 3D real-time cine cardiovascular magnetic resonance (CMR) from highly undersampled data without requiring fully sampled training datasets. Methods: We developed a multi-dynamic low-rank deep image prior (ML-DIP) framework that models spatial image content and deformation fields using separate neural networks. These sub-networks are jointly trained per scan to reconstruct the dynamic image series directly from undersampled k-space data. ML-DIP was evaluated on (i) a 3D cine digital phantom with simulated premature ventricular contractions (PVCs), (ii) ten healthy subjects (including two scanned during both rest and exercise), and (iii) 12 patients with a history of PVCs. Phantom results were assessed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). In vivo performance was evaluated by comparing left-ventricular function quantification (against 2D real-time cine) and image quality (against 2D real-time cine and binning-based 5D-Cine). Results: In the phantom study, ML-DIP achieved PSNR > 29 dB and SSIM > 0.90 for scan times as short as two minutes, while recovering cardiac motion, respiratory motion, and PVC events. In healthy subjects, ML-DIP yielded functional measurements comparable to 2D cine and higher image quality than 5D-Cine, including during exercise with high heart rates and bulk motion. In PVC patients, ML-DIP preserved beat-to-beat variability and reconstructed irregular beats, whereas 5D-Cine showed motion artifacts and information loss due to binning. Conclusion: ML-DIP enables high-quality 3D real-time CMR with acceleration factors exceeding 1,000 by learning low-rank spatial and motion representations from undersampled data, without relying on external fully sampled training datasets.

eess.IV↗

arXiv2025

MegaSR: Mining Customized Semantics and Expressive Guidance for Real-World Image Super-Resolution

Text-to-image (T2I) models have ushered in a new era of real-world image super-resolution (Real-ISR) due to their rich internal implicit knowledge for multimodal learning. Although bringing high-level semantic priors and dense pixel guidance have led to advances in reconstruction, we identified several critical phenomena by analyzing the behavior of existing T2I-based Real-ISR methods: (1) Fine detail deficiency, which ultimately leads to incorrect reconstruction in local regions. (2) Block-wise semantic inconsistency, which results in distracted semantic interpretations across U-Net blocks. (3) Edge ambiguity, which causes noticeable structural degradation. Building upon these observations, we first introduce MegaSR, which enhances the T2I-based Real-ISR models with fine-grained customized semantics and expressive guidance to unlock semantically rich and structurally consistent reconstruction. Then, we propose the Customized Semantics Module (CSM) to supplement fine-grained semantics from the image modality and regulate the semantic fusion between multi-level knowledge to realize customization for different U-Net blocks. Besides the semantic adaptation, we identify expressive multimodal signals through pair-wise comparisons and introduce the Multimodal Signal Fusion Module (MSFM) to aggregate them for structurally consistent reconstruction. Extensive experiments on real-world and synthetic datasets demonstrate the superiority of the method. Notably, it not only achieves state-of-the-art performance on quality-driven metrics but also remains competitive on fidelity-focused metrics, striking a balance between perceptual realism and faithful content reconstruction.

cs.CV↗

arXiv2025

Lateral Deformation of Large-scale Coronal Mass Ejections during the Transition from Non-radial to Radial Propagation

Many coronal mass ejections (CMEs) initially propagate non-radially, and then transition to radial propagation in the corona. This directional transition is a significant process that determines a CME's space weather effects but remains poorly understood. Based on multi-wavelength observations, we investigate the transition from non-radial to radial propagation in the low corona for two large-scale CMEs from the same active region on the solar limb. In the beginning, both CMEs move in a non-radial direction, beneath a system of overlying loops that are roughly parallel to the flux-rope axis. The CMEs laterally deform by bulging their upper flanks in the non-radial stage toward the higher corona, which results in the transition to a radial propagation direction approximately 25$^\circ$ away from the eruption site. After the directional transition, the non-radial-stage upper flank becomes the leading edge in the radial stage. Although the overlying loops do not strap over the flux rope, their strong magnetic tension force constrains the radial expansion of part of the CME during the transition by acting on the flux-rope legs. A major portion of the filament is displaced to the southern part of a CME in the radial stage, which implies the complexity of observational CME features. This study presents the first investigation of the lateral deformation during the transition of CMEs from non-radial to radial in the low corona, and makes an essential contribution to the complete CME evolution picture.

physics.space-ph↗

arXiv2025

CogPlanner: Unveiling the Potential of Agentic Multimodal Retrieval Augmented Generation with Planning

Multimodal Retrieval Augmented Generation (MRAG) systems have shown promise in enhancing the generation capabilities of multimodal large language models (MLLMs). However, existing MRAG frameworks primarily adhere to rigid, single-step retrieval strategies that fail to address real-world challenges of information acquisition and query reformulation. In this work, we introduce the task of Multimodal Retrieval Augmented Generation Planning (MRAG Planning) that aims at effective information seeking and integration while minimizing computational overhead. Specifically, we propose CogPlanner, an agentic plug-and-play framework inspired by human cognitive processes, which iteratively determines query reformulation and retrieval strategies to generate accurate and contextually relevant responses. CogPlanner supports parallel and sequential modeling paradigms. Furthermore, we introduce CogBench, a new benchmark designed to rigorously evaluate the MRAG Planning task and facilitate lightweight CogPlanner integration with resource-efficient MLLMs, such as Qwen2-VL-7B-Cog. Experimental results demonstrate that CogPlanner significantly outperforms existing MRAG baselines, offering improvements in both accuracy and efficiency with minimal additional computational costs.

cs.IR↗

arXiv2025

Trace: Securing Smart Contract Repository Against Access Control Vulnerability

Smart contract vulnerabilities, particularly improper Access Control that allows unauthorized execution of restricted functions, have caused billions of dollars in losses. GitHub hosts numerous smart contract repositories containing source code, documentation, and configuration files-these serve as intermediate development artifacts that must be compiled and packaged before deployment. Third-party developers often reference, reuse, or fork code from these repositories during custom development. However, if the referenced code contains vulnerabilities, it can introduce significant security risks. Existing tools for detecting smart contract vulnerabilities are limited in their ability to handle complex repositories, as they typically require the target contract to be compilable to generate an abstract representation for further analysis. This paper presents TRACE, a tool designed to secure non-compilable smart contract repositories against access control vulnerabilities. TRACE employs LLMs to locate sensitive functions involving critical operations (e.g., transfer) within the contract and subsequently completes function snippets into a fully compilable contract. TRACE constructs a function call graph from the abstract syntax tree (AST) of the completed contract. It uses the control flow graph (CFG) of each function as node information. The nodes of the sensitive functions are then analyzed to detect Access Control vulnerabilities. Experimental results demonstrate that TRACE outperforms state-of-the-art tools on an open-sourced CVE dataset, detecting 14 out of 15 CVEs. In addition, it achieves 89.2% precision on 5,000 recent on-chain contracts, far exceeding the best existing tool at 76.9%. On 83 real-world repositories, TRACE achieves 87.0% precision, significantly surpassing DeepSeek-R1's 14.3%.

cs.SE↗

arXiv2025

Coinvisor: An RL-Enhanced Chatbot Agent for Interactive Cryptocurrency Investment Analysis

The cryptocurrency market offers significant investment opportunities but faces challenges including high volatility and fragmented information. Data integration and analysis are essential for informed investment decisions. Currently, investors use three main approaches: (1) Manual analysis across various sources, which depends heavily on individual experience and is time-consuming and prone to bias; (2) Data aggregation platforms-limited in functionality and depth of analysis; (3) Large language model agents-based on static pretrained models, lacking real-time data integration and multi-step reasoning capabilities. To address these limitations, we present Coinvisor, a reinforcement learning-based chatbot that provides comprehensive analytical support for cryptocurrency investment through a multi-agent framework. Coinvisor integrates diverse analytical capabilities through specialized tools. Its key innovation is a reinforcement learning-based tool selection mechanism that enables multi-step planning and flexible integration of diverse data sources. This design supports real-time interaction and adaptive analysis of dynamic content, delivering accurate and actionable investment insights. We evaluated Coinvisor through automated benchmarks on tool calling accuracy and user studies with 20 cryptocurrency investors using our interface. Results show that Coinvisor improves recall by 40.7% and F1 score by 26.6% over the base model in tool orchestration. User studies show high satisfaction (4.64/5), with participants preferring Coinvisor to both general LLMs and existing crypto platforms (4.62/5).

cs.AI↗

arXiv2025

An efficient approach with theoretical guarantees to simultaneously reconstruct activity and attenuation sinogram for TOF-PET

In positron emission tomography (PET), it is indispensable to perform attenuation correction in order to obtain the quantitatively accurate activity map (tracer distribution) in the body. Generally, this is carried out based on the estimated attenuation map obtained from computed tomography or magnetic resonance imaging. However, except for errors in the attenuation correction factors obtained, the additional scan not only brings in new radiation doses and/or increases the scanning time but also leads to severe misalignment induced by various motions during and between the two sequential scans. To address these issues, based on maximum likelihood estimation, we propose a new mathematical model for simultaneously reconstructing the activity and attenuation sinogram from the time-of-flight (TOF)-PET emission data only. Particularly, we make full use of the exclusively exponential form for the attenuation correction factors, and consider the constraint of a total amount of the activity in some mask region in the proposed model. Furthermore, we prove its well-posedness, including the existence, uniqueness and stability of the solution. We propose an alternating update algorithm to solve the model, and also analyze its convergence. Finally, numerical experiments with various TOF-PET emission data demonstrate that the proposed method is of numerical convergence and robust to noise, and outperforms some state-of-the-art methods in terms of accuracy and efficiency, and has the capability of autonomous attenuation correction.

physics.med-ph↗

arXiv2025

WebRenderBench: Enhancing Web Interface Generation through Layout-Style Consistency and Reinforcement Learning

Automating the conversion of UI images into web code is a critical task for front-end development and rapid prototyping. Advances in multimodal large language models (MLLMs) have made WebUI-to-Code increasingly feasible, yet existing benchmarks remain limited in data diversity and evaluation reliability. To address these issues, we present WebRenderBench, a large-scale benchmark of 45.1k webpages collected from real-world portal sites, offering greater diversity, complexity, and realism than prior benchmarks. We further propose a novel evaluation metric that measures layout and style consistency from the final rendered pages. Unlike vision-based methods that rely on costly LLM reasoning or structure-based comparisons vulnerable to noise and asymmetry, our approach enables more efficient, objective, and reliable UI quality assessment. Finally, we introduce the Automated Layout and Style Inspection Agent (ALISA), which integrates this metric into reinforcement learning as a reward signal to enhance training on crawled asymmetric webpages. Experiments show that ALISA significantly boosts generation performance, achieving state-of-the-art results across multiple metrics.

cs.AI↗

arXiv2025

TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning

Retrieval-Augmented Generation (RAG) has demonstrated considerable effectiveness in open-domain question answering. However, when applied to heterogeneous documents, comprising both textual and tabular components, existing RAG approaches exhibit critical limitations. The prevailing practice of flattening tables and chunking strategies disrupts the intrinsic tabular structure, leads to information loss, and undermines the reasoning capabilities of LLMs in multi-hop, global queries. To address these challenges, we propose TableRAG, an SQL-based framework that unifies textual understanding and complex manipulations over tabular data. TableRAG iteratively operates in four steps: context-sensitive query decomposition, text retrieval, SQL programming and execution, and compositional intermediate answer generation. We also develop HeteQA, a novel benchmark designed to evaluate the multi-hop heterogeneous reasoning capabilities. Experimental results demonstrate that TableRAG consistently outperforms existing baselines on both public datasets and our HeteQA, establishing a new state-of-the-art for heterogeneous document question answering. We release TableRAG at https://github.com/yxh-y/TableRAG/tree/main.

cs.CL↗

arXiv2025

Can LLMs be Good Graph Judge for Knowledge Graph Construction?

In real-world scenarios, most of the data obtained from the information retrieval (IR) system is unstructured. Converting natural language sentences into structured Knowledge Graphs (KGs) remains a critical challenge. We identified three limitations with respect to existing KG construction methods: (1) There could be a large amount of noise in real-world documents, which could result in extracting messy information. (2) Naive LLMs usually extract inaccurate knowledge from some domain-specific documents. (3) Hallucination phenomenon cannot be overlooked when directly using LLMs to construct KGs. In this paper, we propose \textbf{GraphJudge}, a KG construction framework to address the aforementioned challenges. In this framework, we designed an entity-centric strategy to eliminate the noise information in the documents. And we fine-tuned a LLM as a graph judge to finally enhance the quality of generated KGs. Experiments conducted on two general and one domain-specific text-graph pair datasets demonstrate state-of-the-art performance against various baseline methods with strong generalization abilities. Our code is available at \href{https://github.com/hhy-huang/GraphJudge}{https://github.com/hhy-huang/GraphJudge}.

cs.CL↗

arXiv2025

Fracture interactive geodesic active contours for bone segmentation

For bone segmentation, the classical geodesic active contour model is usually limited by its indiscriminate feature extraction, and then struggles to handle the phenomena of edge obstruction, edge leakage and bone fracture. Thus, we propose a fracture interactive geodesic active contour algorithm tailored for bone segmentation, which can better capture bone features and perform robustly to the presence of bone fractures and soft tissues. Inspired by orthopedic knowledge, we construct a novel edge-detector function that combines the intensity and gradient norm, which guides the contour towards bone edges without being obstructed by other soft tissues and therefore reduces mis-segmentation. Furthermore, distance information, where fracture prompts can be embedded, is introduced into the contour evolution as an adaptive step size to stabilize the evolution and help the contour stop at bone edges and fractures. This embedding provides a way to interact with bone fractures and improves the accuracy in the fracture regions. Experiments in pelvic and ankle segmentation demonstrate the effectiveness on addressing the aforementioned problems and show an accurate, stable and consistent performance, indicating a broader application in other bone anatomies. Our algorithm also provides insights into combining the domain knowledge and deep neural networks.

cs.CV↗

arXiv2025

A Comprehensive Survey on Imbalanced Data Learning

With the expansion of data availability, machine learning (ML) has achieved remarkable breakthroughs in both academia and industry. However, imbalanced data distributions are prevalent in various types of raw data and severely hinder the performance of ML by biasing the decision-making processes. To deepen the understanding of imbalanced data and facilitate the related research and applications, this survey systematically analyzes various real-world data formats and concludes existing researches for different data formats into four distinct categories: data re-balancing, feature representation, training strategy, and ensemble learning. This structured analysis helps researchers comprehensively understand the pervasive nature of imbalance across diverse data formats, thereby paving a clearer path toward achieving specific research goals. We provide an overview of relevant open-source libraries, spotlight current challenges, and offer novel insights aimed at fostering future advancements in this critical area of study.

cs.LG↗

arXiv2025

Polynomial complexity of open quantum system problems

Open quantum systems (OQS's) are ubiquitous in non-equilibrium quantum dynamics and in quantum science and technology. Solving the dynamics of an OQS in a quantum many-body bath has been considered a computationally hard problem because of the dimensionality curse. Here, considering that full knowledge of the bath dynamics is unnecessary for describing the reduced dynamics of an OQS, we prove a polynomial complexity theorem, that is, the number of independent equations required to fully describe the dynamics of an OQS increases at most linearly with the evolution time and polynomially with the bath size. Therefore, efficient computational algorithms exist for solving the dynamics of a small-sized OQS (such as a qubit or an atom). We further prove that, when the dynamics of an OQS and the bath is represented by a tensor network, a tensor contraction procedure can be specified such that the bond dimension (i.e., the range of tensor indices contracted in each step) increases only linearly (rather than exponentially) with the evolution time, providing explicitly efficient algorithms for a wide range of OQS's. We demonstrate the theorems and the tensor-network algorithm by solving two widely encountered OQS problems, namely, a spin in a Gaussian bath (the spin-boson model) and a central spin coupled to many environmental spins (the Gaudin model). This work provides approaches to understanding dynamics of OQS's, learning the environments via quantum sensors, and optimizing quantum information processing in noisy environments.

quant-ph↗