arXiv subjects

Xiang Liu

Publications and source records attributed to Xiang Liu.

At least 163 records · Page 9Linked to original sources

arXiv2025

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models

Automated Essay Scoring (AES) plays a crucial role in educational assessment by providing scalable and consistent evaluations of writing tasks. However, traditional AES systems face three major challenges: (1) reliance on handcrafted features that limit generalizability, (2) difficulty in capturing fine-grained traits like coherence and argumentation, and (3) inability to handle multimodal contexts. In the era of Multimodal Large Language Models (MLLMs), we propose EssayJudge, the first multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits. By leveraging MLLMs' strengths in trait-specific scoring and multimodal context understanding, EssayJudge aims to offer precise, context-rich evaluations without manual feature engineering, addressing longstanding AES limitations. Our experiments with 18 representative MLLMs reveal gaps in AES performance compared to human evaluation, particularly in discourse-level traits, highlighting the need for further advancements in MLLM-based AES research.

cs.CL↗

arXiv2025

CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring

Automated Essay Scoring (AES) is crucial for modern education, particularly with the increasing prevalence of multimodal assessments. However, traditional AES methods struggle with evaluation generalizability and multimodal perception, while even recent Multimodal Large Language Model (MLLM)-based approaches can produce hallucinated justifications and scores misaligned with human judgment. To address the limitations, we introduce CAFES, the first collaborative multi-agent framework specifically designed for AES. It orchestrates three specialized agents: an Initial Scorer for rapid, trait-specific evaluations; a Feedback Pool Manager to aggregate detailed, evidence-grounded strengths; and a Reflective Scorer that iteratively refines scores based on this feedback to enhance human alignment. Extensive experiments, using state-of-the-art MLLMs, achieve an average relative improvement of 21% in Quadratic Weighted Kappa (QWK) against ground truth, especially for grammatical and lexical diversity. Our proposed CAFES framework paves the way for an intelligent multimodal AES system. The code will be available upon acceptance.

cs.CL↗

arXiv2025

Non-$D\bar{D}$ Decays into Light Meson Pairs of the $D$-Wave Charmonium $ψ_3(3842)$

As a $D$-wave partner of $ψ(3770)$ identified by the LHCb Collaboration, $ψ_3(3842)$ lies between the $D\bar{D}$ and $D\bar{D^*}$ thresholds. Its non-$D\bar{D}$ decay channels have attracted considerable interest. In this study, we investigate these allowed non-$D\bar{D}$ decays of $ψ_3(3842)$ into $PP$, $PV$, and $VV$ final states using the hadronic loop mechanism, where $P$ and $V$ represent light pseudoscalar and vector mesons, respectively. Our results suggest that these non-$D\bar{D}$ decays of $ψ_3(3842)$ can be significant, with contributions primarily driven by hadronic loops. Notably, the $ρπ$ channel stands out as the main non-$D\bar{D}$ decay mode, while non-$D\bar{D}$ decay channels involving strange mesons are also sizable. These predictions could be tested in future experiments such as those at LHCb and BESIII.

hep-ph↗

arXiv2025

Teach2Eval: An Indirect Evaluation Method for LLM by Judging How It Teaches

Recent progress in large language models (LLMs) has outpaced the development of effective evaluation methods. Traditional benchmarks rely on task-specific metrics and static datasets, which often suffer from fairness issues, limited scalability, and contamination risks. In this paper, we introduce Teach2Eval, an indirect evaluation framework inspired by the Feynman Technique. Instead of directly testing LLMs on predefined tasks, our method evaluates a model's multiple abilities to teach weaker student models to perform tasks effectively. By converting open-ended tasks into standardized multiple-choice questions (MCQs) through teacher-generated feedback, Teach2Eval enables scalable, automated, and multi-dimensional assessment. Our approach not only avoids data leakage and memorization but also captures a broad range of cognitive abilities that are orthogonal to current benchmarks. Experimental results across 26 leading LLMs show strong alignment with existing human and model-based dynamic rankings, while offering additional interpretability for training guidance.

cs.CL↗

arXiv2025

Quotient Complex Transformer (QCformer) for Perovskite Data Analysis

The discovery of novel functional materials is crucial in addressing the challenges of sustainable energy generation and climate change. Hybrid organic-inorganic perovskites (HOIPs) have gained attention for their exceptional optoelectronic properties in photovoltaics. Recently, geometric deep learning, particularly graph neural networks (GNNs), has shown strong potential in predicting material properties and guiding material design. However, traditional GNNs often struggle to capture the periodic structures and higher-order interactions prevalent in such systems. To address these limitations, we propose a novel representation based on quotient complexes (QCs) and introduce the Quotient Complex Transformer (QCformer) for material property prediction. A material structure is modeled as a quotient complex, which encodes both pairwise and many-body interactions via simplices of varying dimensions and captures material periodicity through a quotient operation. Our model leverages higher-order features defined on simplices and processes them using a simplex-based Transformer module. We pretrain QCformer on benchmark datasets such as the Materials Project and JARVIS, and fine-tune it on HOIP datasets. The results show that QCformer outperforms state-of-the-art models in HOIP property prediction, demonstrating its effectiveness. The quotient complex representation and QCformer model together contribute a powerful new tool for predictive modeling of perovskite materials.

cs.LG↗

arXiv2025

Double-bottom centrifugal-barrier molecules dancing with four quarks

Motivated by the recent Belle II measurement of the open-bottom cross section, we perform a systematic study of the double-bottom molecular tetraquark spectrum, including both $S$-wave and $P$-wave configurations. Using the one-boson-exchange potential and the complex scaling method, we investigate the $B^{(*)}\bar{B}^*$ and $B^{(*)}B^*$ systems and predict several bound states and resonances. Our analysis reveals a rich spectrum, including $B\bar{B}^*$ ($0(1^{++})$, $0(0^{-+})$), $B^*\bar{B}^*$ ($0(2^{++})$, $0(0^{-+})$, $0(1^{--})$), $BB^*$ ($0(1^+)$), and $B^*B^*$ ($0(1^+)$) bound states, as well as $B\bar{B}^*$ ($0(1^{--})$, $0(2^{--})$), $B^*\bar{B}^*$ ($0(3^{--})$), $BB^*$ ($0(0^-)$), and $B^*B^*$ ($0(1^-)$, $0(2^-)$) resonances. Our results provide theoretical support for the existence of double-bottom tetraquarks and deliver key benchmarks for future searches at LHCb, Belle II, and other experiments.

hep-ph↗

arXiv2025

Tracking the jet-like corona of black hole Swift J1727.8-1613 during a flare state through Type-C quasi-periodic oscillations

Type-C quasi-periodic oscillations (QPOs) in black hole X-ray transients typically manifest in the low-hard and hard-intermediate states. This study presents a detailed spectral and temporal analysis of the black hole candidate Swift J1727.8-1613 using NICER observations from August and September 2023, with a focus on the first flare period. We detected Type-C QPOs whose centroid frequency increased from 0.33 Hz to 2.63 Hz. An additional increase in frequency was observed when the outburst entered a flare period. The time-averaged spectra, along with the rms and phase-lag spectra of the QPOs, were jointly fitted using the time-dependent Comptonization model vkompthdk to examine the geometry of the corona during this flare. Correlations between spectral and temporal properties suggest that the detected type-C QPOs are primarily modulated by Lense-Thirring precession. Leveraging simultaneous radio observations that indicate discrete jet ejections, we proposed a scenario to describe the co-evolution of the disk-corona-jet during a flare (~3 days). This scenario is partially supported for the first time by polarization data in the soft gamma-ray band from INTEGRAL/IBIS. A phenomenological analysis of the corona scenario was also conducted.

astro-ph.HE↗

arXiv2025

CARE: Compatibility-Aware Incentive Mechanisms for Federated Learning with Budgeted Requesters

Federated learning (FL) is a promising approach that allows requesters (\eg, servers) to obtain local training models from workers (e.g., clients). Since workers are typically unwilling to provide training services/models freely and voluntarily, many incentive mechanisms in FL are designed to incentivize participation by offering monetary rewards from requesters. However, existing studies neglect two crucial aspects of real-world FL scenarios. First, workers can possess inherent incompatibility characteristics (e.g., communication channels and data sources), which can lead to degradation of FL efficiency (e.g., low communication efficiency and poor model generalization). Second, the requesters are budgeted, which limits the amount of workers they can hire for their tasks. In this paper, we investigate the scenario in FL where multiple budgeted requesters seek training services from incompatible workers with private training costs. We consider two settings: the cooperative budget setting where requesters cooperate to pool their budgets to improve their overall utility and the non-cooperative budget setting where each requester optimizes their utility within their own budgets. To address efficiency degradation caused by worker incompatibility, we develop novel compatibility-aware incentive mechanisms, CARE-CO and CARE-NO, for both settings to elicit true private costs and determine workers to hire for requesters and their rewards while satisfying requester budget constraints. Our mechanisms guarantee individual rationality, truthfulness, budget feasibility, and approximation performance. We conduct extensive experiments using real-world datasets to show that the proposed mechanisms significantly outperform existing baselines.

cs.AI↗

arXiv2025

Care for the Mind Amid Chronic Diseases: An Interpretable AI Approach Using IoT

Health sensing for chronic disease management creates immense benefits for social welfare. Existing health sensing studies primarily focus on the prediction of physical chronic diseases. Depression, a widespread complication of chronic diseases, is however understudied. We draw on the medical literature to support depression detection using motion sensor data. To connect humans in this decision-making, safeguard trust, and ensure algorithm transparency, we develop an interpretable deep learning model: Temporal Prototype Network (TempPNet). TempPNet is built upon the emergent prototype learning models. To accommodate the temporal characteristic of sensor data and the progressive property of depression, TempPNet differs from existing prototype learning models in its capability of capturing temporal progressions of prototypes. Extensive empirical analyses using real-world motion sensor data show that TempPNet outperforms state-of-the-art benchmarks in depression detection. Moreover, TempPNet interprets its decision by visualizing the temporal progression of depression and its corresponding symptoms detected from sensor data. We further employ a user study and a medical expert panel to demonstrate its superiority over the benchmarks in interpretability. This study offers an algorithmic solution for impactful social good -- collaborative care of chronic diseases and depression in health sensing. Methodologically, it contributes to extant literature with a novel interpretable deep learning model for depression detection from sensor data. Patients, doctors, and caregivers can deploy our model on mobile devices to monitor patients' depression risks in real-time. Our model's interpretability also allows human experts to participate in the decision-making by reviewing the interpretation and making informed interventions.

cs.AI↗

arXiv2025

Computation and Communication Efficient Lightweighting Vertical Federated Learning for Smart Building IoT

With the increasing number and enhanced capabilities of IoT devices in smart buildings, these devices are evolving beyond basic data collection and control to actively participate in deep learning tasks. Federated Learning (FL), as a decentralized learning paradigm, is well-suited for such scenarios. However, the limited computational and communication resources of IoT devices present significant challenges. While existing research has extensively explored efficiency improvements in Horizontal FL, these techniques cannot be directly applied to Vertical FL due to fundamental differences in data partitioning and model structure. To address this gap, we propose a Lightweight Vertical Federated Learning (LVFL) framework that jointly optimizes computational and communication efficiency. Our approach introduces two distinct lightweighting strategies: one for reducing the complexity of the feature model to improve local computation, and another for compressing feature embeddings to reduce communication overhead. Furthermore, we derive a convergence bound for the proposed LVFL algorithm that explicitly incorporates both computation and communication lightweighting ratios. Experimental results on an image classification task demonstrate that LVFL effectively mitigates resource demands while maintaining competitive learning performance.

cs.LG↗

arXiv2025

TSP-OCS: A Time-Series Prediction for Optimal Camera Selection in Multi-Viewpoint Surgical Video Analysis

Recording the open surgery process is essential for educational and medical evaluation purposes; however, traditional single-camera methods often face challenges such as occlusions caused by the surgeon's head and body, as well as limitations due to fixed camera angles, which reduce comprehensibility of the video content. This study addresses these limitations by employing a multi-viewpoint camera recording system, capturing the surgical procedure from six different angles to mitigate occlusions. We propose a fully supervised learning-based time series prediction method to choose the best shot sequences from multiple simultaneously recorded video streams, ensuring optimal viewpoints at each moment. Our time series prediction model forecasts future camera selections by extracting and fusing visual and semantic features from surgical videos using pre-trained models. These features are processed by a temporal prediction network with TimeBlocks to capture sequential dependencies. A linear embedding layer reduces dimensionality, and a Softmax classifier selects the optimal camera view based on the highest probability. In our experiments, we created five groups of open thyroidectomy videos, each with simultaneous recordings from six different angles. The results demonstrate that our method achieves competitive accuracy compared to traditional supervised methods, even when predicting over longer time horizons. Furthermore, our approach outperforms state-of-the-art time series prediction techniques on our dataset. This manuscript makes a unique contribution by presenting an innovative framework that advances surgical video analysis techniques, with significant implications for improving surgical education and patient safety.

cs.CV↗

arXiv2025

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation

Large Multimodal Models (LMMs) have demonstrated impressive capabilities in multimodal understanding and generation, pushing forward advancements in text-to-image generation. However, achieving accurate text-image alignment for LMMs, particularly in compositional scenarios, remains challenging. Existing approaches, such as layout planning for multi-step generation and learning from human feedback or AI feedback, depend heavily on prompt engineering, costly human annotations, and continual upgrading, limiting flexibility and scalability. In this work, we introduce a model-agnostic iterative self-improvement framework (SILMM) that can enable LMMs to provide helpful and scalable self-feedback and optimize text-image alignment via Direct Preference Optimization (DPO). DPO can readily applied to LMMs that use discrete visual tokens as intermediate image representations; while it is less suitable for LMMs with continuous visual features, as obtaining generation probabilities is challenging. To adapt SILMM to LMMs with continuous features, we propose a diversity mechanism to obtain diverse representations and a kernel-based continuous DPO for alignment. Extensive experiments on three compositional text-to-image generation benchmarks validate the effectiveness and superiority of SILMM, showing improvements exceeding 30% on T2I-CompBench++ and around 20% on DPG-Bench.

cs.CV↗

arXiv2025

Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation

Category-level object pose estimation aims to determine the pose and size of novel objects in specific categories. Existing correspondence-based approaches typically adopt point-based representations to establish the correspondences between primitive observed points and normalized object coordinates. However, due to the inherent shape-dependence of canonical coordinates, these methods suffer from semantic incoherence across diverse object shapes. To resolve this issue, we innovatively leverage the sphere as a shared proxy shape of objects to learn shape-independent transformation via spherical representations. Based on this insight, we introduce a novel architecture called SpherePose, which yields precise correspondence prediction through three core designs. Firstly, We endow the point-wise feature extraction with SO(3)-invariance, which facilitates robust mapping between camera coordinate space and object coordinate space regardless of rotation transformation. Secondly, the spherical attention mechanism is designed to propagate and integrate features among spherical anchors from a comprehensive perspective, thus mitigating the interference of noise and incomplete point cloud. Lastly, a hyperbolic correspondence loss function is designed to distinguish subtle distinctions, which can promote the precision of correspondence prediction. Experimental results on CAMERA25, REAL275 and HouseCat6D benchmarks demonstrate the superior performance of our method, verifying the effectiveness of spherical representations and architectural innovations.

cs.CV↗

arXiv2025

State Space Model Meets Transformer: A New Paradigm for 3D Object Detection

DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features in the transformer decoder remain fixed, leading to minimal contributions from later decoder layers, thereby limiting performance improvement. Recently, State Space Models (SSM) have shown efficient context modeling ability with linear complexity through iterative interactions between system states and inputs. Inspired by SSMs, we propose a new 3D object DEtection paradigm with an interactive STate space model (DEST). In the interactive SSM, we design a novel state-dependent SSM parameterization method that enables system states to effectively serve as queries in 3D indoor detection tasks. In addition, we introduce four key designs tailored to the characteristics of point cloud and SSM: The serialization and bidirectional scanning strategies enable bidirectional feature interaction among scene points within the SSM. The inter-state attention mechanism models the relationships between state points, while the gated feed-forward network enhances inter-channel correlations. To the best of our knowledge, this is the first method to model queries as system states and scene points as system inputs, which can simultaneously update scene point features and query features with linear complexity. Extensive experiments on two challenging datasets demonstrate the effectiveness of our DEST-based method. Our method improves the GroupFree baseline in terms of AP50 on ScanNet V2 (+5.3) and SUN RGB-D (+3.2) datasets. Based on the VDETR baseline, Our method sets a new SOTA on the ScanNetV2 and SUN RGB-D datasets.

cs.CV↗

arXiv2025

Optimizing for the Shortest Path in Denoising Diffusion Model

In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and insights from graph theory, our model, termed the Shortest Path Diffusion Model (ShortDF), treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error. By optimizing the initial residuals, we improve the efficiency of the reverse diffusion process and the quality of the generated samples. Extensive experiments on multiple standard benchmarks demonstrate that ShortDF significantly reduces diffusion time (or steps) while enhancing the visual fidelity of generated samples compared to prior arts. This work, we suppose, paves the way for interactive diffusion-based applications and establishes a foundation for rapid data generation. Code is available at https://github.com/UnicomAI/ShortDF.

cs.CV↗

arXiv2025

Role of $4S$-$3D$ mixing in explaining the $ω$-like $Y(2119)$ observed in $e^+e^-\toρπ$ and $ρ(1450)π$

The BESIII Collaboration has recently reported a new resonance structure in the cross-section analyses of the $e^+e^- \to ρπ$ and $e^+e^- \to ρ(1450)π$ processes, displaying characteristics akin to an $ω$-meson. However, its measured mass, $M = 2119 \pm 11 \pm 15 \, \text{MeV}$, significantly deviates from the predictions of the unquenched relativized potential model for conventional $ω$ vector meson spectroscopy. To address this discrepancy, we propose a $4S$-$3D$ mixing scheme and investigate the corresponding decay properties within this framework. Our analysis demonstrates that the mixed state $ω_{4S\text{-}3D}^\prime$ exhibits excellent agreement with the observed resonance, not only in mass and width but also in the products of its dielectron width and branching ratios, $Γ_{e^+e^-}^{\mathcal{R}}\times\mathcal{B}_{\mathcal{R}\toρπ}$ and $Γ_{e^+e^-}^{\mathcal{R}}\times\mathcal{B}_{\mathcal{R}\toρ(1450)π\toπ^+π^-π^0}$. The determined mixing angle, $θ= -\left(31.1^{+2.1}_{-3.1}\right)\degree$, strongly supports the interpretation of this structure as the $ω_{4S\text{-}3D}^\prime$ state. Furthermore, we predict dominant decay channels for $ω_{4S\text{-}3D}^\prime$ and its partner state $ω_{4S\text{-}3D}^{\prime\prime}$. These predictions, together with the proposed mixing mechanism, provide crucial guidance for future experimental studies aimed at probing this structure and rigorously testing the $4S$-$3D$ mixing hypothesis.

hep-ph↗

arXiv2025

A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis

While conversational generative AI has shown considerable potential in enhancing decision-making for agricultural professionals, its exploration has predominantly been anchored in text-based interactions. The evolution of multimodal conversational AI, leveraging vast amounts of image-text data from diverse sources, marks a significant stride forward. However, the application of such advanced vision-language models in the agricultural domain, particularly for crop disease diagnosis, remains underexplored. In this work, we present the crop disease domain multimodal (CDDM) dataset, a pioneering resource designed to advance the field of agricultural research through the application of multimodal learning techniques. The dataset comprises 137,000 images of various crop diseases, accompanied by 1 million question-answer pairs that span a broad spectrum of agricultural knowledge, from disease identification to management practices. By integrating visual and textual data, CDDM facilitates the development of sophisticated question-answering systems capable of providing precise, useful advice to farmers and agricultural professionals. We demonstrate the utility of the dataset by finetuning state-of-the-art multimodal models, showcasing significant improvements in crop disease diagnosis. Specifically, we employed a novel finetuning strategy that utilizes low-rank adaptation (LoRA) to finetune the visual encoder, adapter and language model simultaneously. Our contributions include not only the dataset but also a finetuning strategy and a benchmark to stimulate further research in agricultural technology, aiming to bridge the gap between advanced AI techniques and practical agricultural applications. The dataset is available at https: //github.com/UnicomAI/UnicomBenchmark/tree/main/CDDMBench.

cs.CV↗

arXiv2025

Discovery potential of charmonium $2P$ states through the $e^+e^- \to γD\bar{D}$ processes

In this work, we investigate the production of charmonium $2P$ states via the $e^+e^-\to γD\bar{D}$ process at $\sqrt{s} = 4.23$ GeV. Using the measured cross-section data for $e^+e^-\to γX(3872)$ as a reference, we calculate the cross sections for $e^+e^-\to γχ_{c0}(2P)$ and $e^+e^-\to γχ_{c2}(2P)$. Since the $χ_{c0}(2P)$ and $χ_{c2}(2P)$ states predominantly decay into $D\bar{D}$ final states, we also predict the corresponding $D\bar{D}$ invariant mass spectrum for the $e^+e^-\to γD\bar{D}$ process. Our results indicate that $e^+e^-\to γD\bar{D}$ is an ideal process for identifying the $χ_{c0}(2P)$ and $χ_{c2}(2P)$ states, analogous to the $γγ\to D\bar{D}$ and $B^+\to D^+D^-K^+$ processes. This study highlights the discovery potential of charmonium $2P$ states at BESIII and Belle II.

hep-ph↗