arXiv subjects

Jin Hao

Publications and source records attributed to Jin Hao.

15 recordsLinked to original sources

arXiv2026

DentAgent: Evidence-Centric Multi-Agent Coordination for Multimodal Dental Reasoning

Oral diseases affect billions of people worldwide, underscoring a pressing need for accurate and reliable dental assessment that integrates heterogeneous evidence from domain knowledge, radiographs, intraoral photographs, and 3D dental data. Most existing dental AI systems remain modality- or task-specific. Although recent vision-language models support flexible dental question answering, directly generated response leaves evidence implicit and untraceable. To address these limitations, we introduce DentAgent, an evidence-centric multi-agent framework, in which the Orchestrator coordinate five specialized agents spanning various modalities. Each specialist utilizes domain tools to convert observations into structured evidence records. The Evidence Blackboard manages these records as a shared evidence state, tracking coverage, gaps, and conflicts before response generation. This standardized evidence representation integrates isolated dental capabilities into a unified agentic workflow. Across four benchmarks, DentAgent demonstrates leading performance, even surpassing the senior specialists by 17.3 percentage points on multi-label diagnosis, which supports its value for broadly applicable and traceable multimodal dental reasoning, and highlights its potential as a technical foundation for population oral health assessment and management.

cs.AI↗

arXiv2026

Unified study of scalar, vector and tensor two-meson form factors in $U(3)$ resonance chiral theory

We perform a systematic study of two-meson form factors of the scalar, vector, and anti-symmetric tensor types within the framework of the $U(3)$ resonance chiral theory. The complete perturbative form factors in both the strangeness-conserving and strangeness-changing channels are calculated by incorporating one-loop light-flavor pseudoscalar meson contributions and tree-level resonance exchanges. With these newly calculated chiral results, we construct the corresponding unitarized form factors by incorporating meson-meson final-state interactions. The parameter values obtained in previous meson-meson scattering studies are then exploited to predict the corresponding form factors. Different types of form factors are found to exhibit rather distinct resonance structures across channels.

hep-ph↗

arXiv2026

Axion-like particle-meson production in semileptonic $\tau$ decays

In this work we explore the semileptonic $\tau$ decays into the axion-like particle ($a$)-meson final states within chiral effective field theory. The next-to-leading-order mixing matrix for the $\pi^0$-$\eta$-$\eta'$-$a$ system with the linear isospin-breaking effects, is exploited and then implemented to calculate the hadronic form factors relevant to the $\tau$ decays. The resonance parameters entering the form factors are determined from fits to the experimental spectra of $\tau^- \to \pi^- \pi^0 \nu_\tau$, $\tau^- \to K_S \pi^- \nu_\tau$, and $\tau^- \to K^- \eta \nu_\tau$. We then focus on the predictions to the branching ratios, invariant-mass distributions, and forward-backward asymmetries from the $\tau^-\to P a \nu_\tau$ processes, with $P=\pi^-$ and $K^-$. Our results provide a quantitative basis for future searches of the axion-like particle signals in semileptonic $\tau$ decays.

hep-ph↗

arXiv2025

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Real-world clinical decision-making requires integrating heterogeneous data, including medical text, 2D images, 3D volumes, and videos, while existing AI systems fail to unify all these signals, limiting their utility. In this paper, we introduce Hulu-Med, a transparent, generalist medical Vision-Language Model (VLM) designed to unify language-only, 2D/3D vision-language, and video understanding within a single architecture. Hulu-Med is trained on a curated corpus of 16.7 million samples, comprising exclusively public or synthetic data, spanning 12 major anatomical systems and 14 medical imaging modalities. Hulu-Med employs a medical-aware token-reduction strategy that prunes redundant visual tokens, achieving up to a 55% reduction for 3D and video inputs, improving cross-modal efficiency, and enabling training at 7B-32B parameter scales in approximately 4,000-40,000 GPU hours. Across 30 public in-domain and out-of-domain medical benchmarks-covering text reasoning, visual question answering, report generation, multilingual dialogue, video understanding, and rare disease diagnosis-Hulu-Med surpasses existing open-source models on 27 of 30 benchmarks and outperforms proprietary systems such as GPT-4o on 16 benchmarks. Despite being a VLM, Hulu-Med outperforms GPT-4o and matches GPT-o1 on the text-only HealthBench. For the first time in the community, we provide a fully transparent, reproducible and cost-effective pipeline for holistic medical vision-language understanding by releasing our end-to-end data curation, training procedures, and model parameters. Code and models are available at https://github.com/ZJUI-AI4H/Hulu-Med.

cs.CV↗

arXiv2025

Revisit of the electromagnetic correction to $\tau\to\pi\pi\nu_\tau$ and its implication for muon $g-2$ based on $\tau$ data

In this work we focus on the evaluation of the leading-order hadronic vacuum polarization contribution from the $\pi\pi$ channel to the muon anomalous magnetic moment $a_\mu$ by using the experimental $\tau\to\pi\pi\nu_\tau$ data. The isospin breaking corrections play the decisive role in this approach of computing $a_\mu$. One of such important isospin breaking sources is the long-distance electromagnetic correction factor $G_{\rm EM}$ of the $\tau\to\pi\pi\nu_\tau$ process from the real photon radiation. The latter effect can be calculated from the $\tau\to\pi\pi\nu_\tau\gamma$ amplitude, which is revised in this work within the resonance chiral theory by simultaneously including the even-intrinsic-parity and odd-intrinsic-parity resonance operators. We update the determination of the only unknown resonance coupling through the $\omega\to\pi^0\pi^0\gamma$ decay by including contributions from both the vector and scalar resonances. By taking other remaining contributions from the muon $g-2$ White Paper 2025, we further revise the complete value of $a_\mu$, which turns out to deviate from the newest world average result after Fermilab's measurement at the level of 2.7 $\sigma$.

hep-ph↗

arXiv2025

DentVLM: A Multimodal Vision-Language Model for Comprehensive Dental Diagnosis and Enhanced Clinical Practice

Diagnosing and managing oral diseases necessitate advanced visual interpretation across diverse imaging modalities and integrated information synthesis. While current AI models excel at isolated tasks, they often fall short in addressing the complex, multimodal requirements of comprehensive clinical dental practice. Here we introduce DentVLM, a multimodal vision-language model engineered for expert-level oral disease diagnosis. DentVLM was developed using a comprehensive, large-scale, bilingual dataset of 110,447 images and 2.46 million visual question-answering (VQA) pairs. The model is capable of interpreting seven 2D oral imaging modalities across 36 diagnostic tasks, significantly outperforming leading proprietary and open-source models by 19.6% higher accuracy for oral diseases and 27.9% for malocclusions. In a clinical study involving 25 dentists, evaluating 1,946 patients and encompassing 3,105 QA pairs, DentVLM surpassed the diagnostic performance of 13 junior dentists on 21 of 36 tasks and exceeded that of 12 senior dentists on 12 of 36 tasks. When integrated into a collaborative workflow, DentVLM elevated junior dentists' performance to senior levels and reduced diagnostic time for all practitioners by 15-22%. Furthermore, DentVLM exhibited promising performance across three practical utility scenarios, including home-based dental health management, hospital-based intelligent diagnosis and multi-agent collaborative interaction. These findings establish DentVLM as a robust clinical decision support tool, poised to enhance primary dental care, mitigate provider-patient imbalances, and democratize access to specialized medical expertise within the field of dentistry.

cs.CV↗

arXiv2025

Unified study of two-meson and axion-meson production from semileptonic tau decays within resonance chiral framework

We carry out the joint study of the semileptonic tau decays into the two-meson and axion-meson channels, viz. $\tau^-\to (P_1P_2)^-\nu_\tau$ and $\tau^-\to \pi^-(K^-) a\nu_\tau$ within the framework of resonance chiral theory by including the model-independent axion-gluon-gluon interaction. By utilizing the $\pi^0$-$\eta$-$\eta'$-axion mixing matrix elements from recent studies, we calculate the pertinent two-pseudoscalar boson form factors. To simultaneously fit the experimental spectra measured in the Cabibbo allowed $\tau^-\to \pi^-\pi^0\nu_\tau$ process and also the Cabibbo suppressed $\tau^-\to(K_S\pi^-, K^-\eta)\nu_\tau$ ones, we determine all the relevant hadron resonance parameters. Then we give predictions to the spectra and branching ratios for various channels, such as $\tau^-\to(\pi^-\eta,\pi^-\eta',K^-\eta',\pi^-a,K^-a)\nu_\tau$. We also calculate the forward-backward asymmetries for all the aforementioned channels. The interplay between the scalar and vector form factors for different observables is analyzed in detail. Our theoretical predictions supply useful guidance to the future tau experiments, such as those at Belle-II, Super Tau-Charm Facility and Tera-Z factory of Circular Electron-Positron Collider.

hep-ph↗

arXiv2024

Isospin-breaking contribution to the model-independent axion-photon-photon coupling in $U(3)$ chiral theory

We pursue the calculation of the model-independent component of the axion-photon-photon coupling in the $U(3)$ chiral perturbation theory up to next-to-leading order, with the emphasis on the isospin breaking effect. The mixing of the $\pi^0$-$\eta$-$\eta'$-axion system is revised as well by working out the complete linear isospin-breaking terms. Our calculation shows that the isospin-breaking correction to the axion-photon-photon coupling amounts to more than 15%, comparing with the result in the isospin limit.

hep-ph↗

arXiv2023

TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer

Optical Intraoral Scanners (IOS) are widely used in digital dentistry to provide detailed 3D information of dental crowns and the gingiva. Accurate 3D tooth segmentation in IOSs is critical for various dental applications, while previous methods are error-prone at complicated boundaries and exhibit unsatisfactory results across patients. In this paper, we propose TSegFormer which captures both local and global dependencies among different teeth and the gingiva in the IOS point clouds with a multi-task 3D transformer architecture. Moreover, we design a geometry-guided loss based on a novel point curvature to refine boundaries in an end-to-end manner, avoiding time-consuming post-processing to reach clinically applicable segmentation. In addition, we create a dataset with 16,000 IOSs, the largest ever IOS dataset to the best of our knowledge. The experimental results demonstrate that our TSegFormer consistently surpasses existing state-of-the-art baselines. The superiority of TSegFormer is corroborated by extensive analysis, visualizations and real-world clinical applicability tests. Our code is available at https://github.com/huiminxiong/TSegFormer.

cs.CV↗

arXiv2023

Fast Model Debias with Machine Unlearning

Recent discoveries have revealed that deep neural networks might behave in a biased manner in many real-world scenarios. For instance, deep networks trained on a large-scale face recognition dataset CelebA tend to predict blonde hair for females and black hair for males. Such biases not only jeopardize the robustness of models but also perpetuate and amplify social biases, which is especially concerning for automated decision-making processes in healthcare, recruitment, etc., as they could exacerbate unfair economic and social inequalities among different groups. Existing debiasing methods suffer from high costs in bias labeling or model re-training, while also exhibiting a deficiency in terms of elucidating the origins of biases within the model. To this respect, we propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases inherent in trained models. The FMD identifies biased attributes through an explicit counterfactual concept and quantifies the influence of data samples with influence functions. Moreover, we design a machine unlearning-based strategy to efficiently and effectively remove the bias in a trained model with a small counterfactual dataset. Experiments on the Colored MNIST, CelebA, and Adult Income datasets along with experiments with large language models demonstrate that our method achieves superior or competing accuracies compared with state-of-the-art methods while attaining significantly fewer biases and requiring much less debiasing cost. Notably, our method requires only a small external dataset and updating a minimal amount of model parameters, without the requirement of access to training data that may be too large or unavailable in practice.

cs.LG↗

arXiv2023

Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer

Data privacy and long-tailed distribution are the norms rather than the exception in many real-world tasks. This paper investigates a federated long-tailed learning (Fed-LT) task in which each client holds a locally heterogeneous dataset; if the datasets can be globally aggregated, they jointly exhibit a long-tailed distribution. Under such a setting, existing federated optimization and/or centralized long-tailed learning methods hardly apply due to challenges in (a) characterizing the global long-tailed distribution under privacy constraints and (b) adjusting the local learning strategy to cope with the head-tail imbalance. In response, we propose a method termed $\texttt{Fed-GraB}$, comprised of a Self-adjusting Gradient Balancer (SGB) module that re-weights clients' gradients in a closed-loop manner, based on the feedback of global long-tailed distribution evaluated by a Direct Prior Analyzer (DPA) module. Using $\texttt{Fed-GraB}$, clients can effectively alleviate the distribution drift caused by data heterogeneity during the model training process and obtain a global model with better performance on the minority classes while maintaining the performance of the majority classes. Extensive experiments demonstrate that $\texttt{Fed-GraB}$ achieves state-of-the-art performance on representative datasets such as CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist.

cs.LG↗

arXiv2023

On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning

Though Self-supervised learning (SSL) has been widely studied as a promising technique for representation learning, it doesn't generalize well on long-tailed datasets due to the majority classes dominating the feature space. Recent work shows that the long-tailed learning performance could be boosted by sampling extra in-domain (ID) data for self-supervised training, however, large-scale ID data which can rebalance the minority classes are expensive to collect. In this paper, we propose an alternative but easy-to-use and effective solution, Contrastive with Out-of-distribution (OOD) data for Long-Tail learning (COLT), which can effectively exploit OOD data to dynamically re-balance the feature space. We empirically identify the counter-intuitive usefulness of OOD samples in SSL long-tailed learning and principally design a novel SSL method. Concretely, we first localize the `head' and `tail' samples by assigning a tailness score to each OOD sample based on its neighborhoods in the feature space. Then, we propose an online OOD sampling strategy to dynamically re-balance the feature space. Finally, we enforce the model to be capable of distinguishing ID and OOD samples by a distribution-level supervised contrastive loss. Extensive experiments are conducted on various datasets and several state-of-the-art SSL frameworks to verify the effectiveness of the proposed method. The results show that our method significantly improves the performance of SSL on long-tailed datasets by a large margin, and even outperforms previous work which uses external ID data. Our code is available at https://github.com/JianhongBai/COLT.

cs.CV↗

arXiv2022

OrthoGAN:High-Precision Image Generation for Teeth Orthodontic Visualization

Patients take care of what their teeth will be like after the orthodontics. Orthodontists usually describe the expectation movement based on the original smile images, which is unconvincing. The growth of deep-learning generative models change this situation. It can visualize the outcome of orthodontic treatment and help patients foresee their future teeth and facial appearance. While previous studies mainly focus on 2D or 3D virtual treatment outcome (VTO) at a profile level, the problem of simulating treatment outcome at a frontal facial image is poorly explored. In this paper, we build an efficient and accurate system for simulating virtual teeth alignment effects in a frontal facial image. Our system takes a frontal face image of a patient with visible malpositioned teeth and the patient's 3D scanned teeth model as input, and progressively generates the visual results of the patient's teeth given the specific orthodontics planning steps from the doctor (i.e., the specification of translations and rotations of individual tooth). We design a multi-modal encoder-decoder based generative model to synthesize identity-preserving frontal facial images with aligned teeth. In addition, the original image color information is used to optimize the orthodontic outcomes, making the results more natural. We conduct extensive qualitative and clinical experiments and also a pilot study to validate our method.

cs.CV↗

arXiv2022

TFormer: 3D Tooth Segmentation in Mesh Scans with Geometry Guided Transformer

Optical Intra-oral Scanners (IOS) are widely used in digital dentistry, providing 3-Dimensional (3D) and high-resolution geometrical information of dental crowns and the gingiva. Accurate 3D tooth segmentation, which aims to precisely delineate the tooth and gingiva instances in IOS, plays a critical role in a variety of dental applications. However, segmentation performance of previous methods are error-prone in complicated tooth-tooth or tooth-gingiva boundaries, and usually exhibit unsatisfactory results across various patients, yet the clinically applicability is not verified with large-scale dataset. In this paper, we propose a novel method based on 3D transformer architectures that is evaluated with large-scale and high-resolution 3D IOS datasets. Our method, termed TFormer, captures both local and global dependencies among different teeth to distinguish various types of teeth with divergent anatomical structures and confusing boundaries. Moreover, we design a geometry guided loss based on a novel point curvature to exploit boundary geometric features, which helps refine the boundary predictions for more accurate and smooth segmentation. We further employ a multi-task learning scheme, where an additional teeth-gingiva segmentation head is introduced to improve the performance. Extensive experimental results in a large-scale dataset with 16,000 IOS, the largest IOS dataset to our best knowledge, demonstrate that our TFormer can surpass existing state-of-the-art baselines with a large margin, with its utility in real-world scenarios verified by a clinical applicability test.

cs.CV↗

arXiv2022

AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications

A critical step in virtual dental treatment planning is to accurately delineate all tooth-bone structures from CBCT with high fidelity and accurate anatomical information. Previous studies have established several methods for CBCT segmentation using deep learning. However, the inherent resolution discrepancy of CBCT and the loss of occlusal and dentition information largely limited its clinical applicability. Here, we present a Deep Dental Multimodal Analysis (DDMA) framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model (the most accurate digital dental model), and a fusion model to generate 3D fused crown-root-bone structures with high fidelity and accurate occlusal and dentition information. Our model was trained with a large-scale dataset with 503 CBCT and 28,559 IOS meshes manually annotated by experienced human experts. For CBCT segmentation, we use a five-fold cross validation test, each with 50 CBCT, and our model achieves an average Dice coefficient and IoU of 93.99% and 88.68%, respectively, significantly outperforming the baselines. For IOS segmentations, our model achieves an mIoU of 93.07% and 95.70% on the maxillary and mandible on a test set of 200 IOS meshes, which are 1.77% and 3.52% higher than the state-of-art method. Our DDMA framework takes about 20 to 25 minutes to generate the fused 3D mesh model following the sequential processing order, compared to over 5 hours by human experts. Notably, our framework has been incorporated into a software by a clear aligner manufacturer, and real-world clinical cases demonstrate that our model can visualize crown-root-bone structures during the entire orthodontic treatment and can predict risks like dehiscence and fenestration. These findings demonstrate the potential of multi-modal deep learning to improve the quality of digital dental models and help dentists make better clinical decisions.

eess.IV↗