arXiv subjects

Xiaoqiang Liu

Publications and source records attributed to Xiaoqiang Liu.

At least 37 records · Page 2Linked to original sources

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

VC-Agent: An Interactive Agent for Customized Video Dataset Collection

Facing scaling laws, video data from the internet becomes increasingly important. However, collecting extensive videos that meet specific needs is extremely labor-intensive and time-consuming. In this work, we study the way to expedite this collection process and propose VC-Agent, the first interactive agent that is able to understand users' queries and feedback, and accordingly retrieve/scale up relevant video clips with minimal user input. Specifically, considering the user interface, our agent defines various user-friendly ways for the user to specify requirements based on textual descriptions and confirmations. As for agent functions, we leverage existing multi-modal large language models to connect the user's requirements with the video content. More importantly, we propose two novel filtering policies that can be updated when user interaction is continually performed. Finally, we provide a new benchmark for personalized video dataset collection, and carefully conduct the user study to verify our agent's usage in various real scenarios. Extensive experiments demonstrate the effectiveness and efficiency of our agent for customized video dataset collection. Project page: https://allenyidan.github.io/vcagent_page/.

cs.AI↗

arXiv2025

OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers

Lip synchronization is the task of aligning a speaker's lip movements in video with corresponding speech audio, and it is essential for creating realistic, expressive video content. However, existing methods often rely on reference frames and masked-frame inpainting, which limit their robustness to identity consistency, pose variations, facial occlusions, and stylized content. In addition, since audio signals provide weaker conditioning than visual cues, lip shape leakage from the original video will affect lip sync quality. In this paper, we present OmniSync, a universal lip synchronization framework for diverse visual scenarios. Our approach introduces a mask-free training paradigm using Diffusion Transformer models for direct frame editing without explicit masks, enabling unlimited-duration inference while maintaining natural facial dynamics and preserving character identity. During inference, we propose a flow-matching-based progressive noise initialization to ensure pose and identity consistency, while allowing precise mouth-region editing. To address the weak conditioning signal of audio, we develop a Dynamic Spatiotemporal Classifier-Free Guidance (DS-CFG) mechanism that adaptively adjusts guidance strength over time and space. We also establish the AIGC-LipSync Benchmark, the first evaluation suite for lip synchronization in diverse AI-generated videos. Extensive experiments demonstrate that OmniSync significantly outperforms prior methods in both visual quality and lip sync accuracy, achieving superior results in both real-world and AI-generated videos.

cs.CV↗

arXiv2025

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.

cs.CV↗

arXiv2025

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation

Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains challenging to existing methods, which often struggle with heavy computational cost and limited controllability. In this work, we introduce an autoregressive video generation framework that enables interactive multimodal control and low-latency extrapolation in a streaming manner. With minimal modifications to a standard large language model (LLM), our framework accepts multimodal condition encodings including audio, pose, and text, and outputs spatially and semantically coherent representations to guide the denoising process of a diffusion head. To support this, we construct a large-scale dialogue dataset of approximately 20,000 hours from multiple sources, providing rich conversational scenarios for training. We further introduce a deep compression autoencoder with up to 64$\times$ reduction ratio, which effectively alleviates the long-horizon inference burden of the autoregressive model. Extensive experiments on duplex conversation, multilingual human synthesis, and interactive world model highlight the advantages of our approach in low latency, high efficiency, and fine-grained multimodal controllability.

cs.CV↗

arXiv2025

GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation

Creating high-quality, generalizable speech-driven 3D talking heads remains a persistent challenge. Previous methods achieve satisfactory results for fixed viewpoints and small-scale audio variations, but they struggle with large head rotations and out-of-distribution (OOD) audio. Moreover, they are constrained by the need for time-consuming, identity-specific training. We believe the core issue lies in the lack of sufficient 3D priors, which limits the extrapolation capabilities of synthesized talking heads. To address this, we propose GGTalker, which synthesizes talking heads through a combination of generalizable priors and identity-specific adaptation. We introduce a two-stage Prior-Adaptation training strategy to learn Gaussian head priors and adapt to individual characteristics. We train Audio-Expression and Expression-Visual priors to capture the universal patterns of lip movements and the general distribution of head textures. During the Customized Adaptation, individual speaking styles and texture details are precisely modeled. Additionally, we introduce a color MLP to generate fine-grained, motion-aligned textures and a Body Inpainter to blend rendered results with the background, producing indistinguishable, photorealistic video frames. Comprehensive experiments show that GGTalker achieves state-of-the-art performance in rendering quality, 3D consistency, lip-sync accuracy, and training efficiency.

cs.CV↗

arXiv2025

MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding

Multimodal large language models (MLLMs) recently showed strong capacity in integrating data among multiple modalities, empowered by a generalizable attention architecture. Advanced methods predominantly focus on language-centric tuning while less exploring multimodal tokens mixed through attention, posing challenges in high-level tasks that require fine-grained cognition and emotion understanding. In this work, we identify the attention deficit disorder problem in multimodal learning, caused by inconsistent cross-modal attention and layer-by-layer decayed attention activation. To address this, we propose a novel attention mechanism, termed MOdular Duplex Attention (MODA), simultaneously conducting the inner-modal refinement and inter-modal interaction. MODA employs a correct-after-align strategy to effectively decouple modality alignment from cross-layer token mixing. In the alignment phase, tokens are mapped to duplex modality spaces based on the basis vectors, enabling the interaction between visual and language modality. Further, the correctness of attention scores is ensured through adaptive masked attention, which enhances the model's flexibility by allowing customizable masking patterns for different modalities. Extensive experiments on 21 benchmark datasets verify the effectiveness of MODA in perception, cognition, and emotion tasks. Source code and demo are available in https://zzcheng.top/MODA.

cs.CV↗

arXiv2025

Fully First-Principles Approach in Studying Topological Magnons

We develop a fully first-principles approach for spin dynamics based on density functional perturbation theory. We demonstrate that the magnon wavefunction can be expressed by a set of electronic wavefunctions obtained from the decomposition of magnon density profile, enabling the direct calculation of magnonic quantities including Berry curvature and Chern number. As a concrete example, we show that monolayer CrI$_3$ can host topological magnons driven by spin-orbit coupling. Our model-free approach paves the way for the comprehensive studies of magnons in real materials.

cond-mat.mtrl-sci↗

arXiv2025

Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control

Speech-driven 3D talking face method should offer both accurate lip synchronization and controllable expressions. Previous methods solely adopt discrete emotion labels to globally control expressions throughout sequences while limiting flexible fine-grained facial control within the spatiotemporal domain. We propose a diffusion-transformer-based 3D talking face generation model, Cafe-Talk, which simultaneously incorporates coarse- and fine-grained multimodal control conditions. Nevertheless, the entanglement of multiple conditions challenges achieving satisfying performance. To disentangle speech audio and fine-grained conditions, we employ a two-stage training pipeline. Specifically, Cafe-Talk is initially trained using only speech audio and coarse-grained conditions. Then, a proposed fine-grained control adapter gradually adds fine-grained instructions represented by action units (AUs), preventing unfavorable speech-lip synchronization. To disentangle coarse- and fine-grained conditions, we design a swap-label training mechanism, which enables the dominance of the fine-grained conditions. We also devise a mask-based CFG technique to regulate the occurrence and intensity of fine-grained control. In addition, a text-based detector is introduced with text-AU alignment to enable natural language user input and further support multimodal control. Extensive experimental results prove that Cafe-Talk achieves state-of-the-art lip synchronization and expressiveness performance and receives wide acceptance in fine-grained control in user studies. Project page: https://harryxd2018.github.io/cafe-talk/

cs.CV↗

arXiv2025

LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an appearance reference, with motion (i.e., facial expressions and head pose) derived from a driving video, audio, text, or generation. Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability. Building upon this, we develop a video-driven portrait animation framework named LivePortrait with a focus on better generalization, controllability, and efficiency for practical usage. To enhance the generation quality and generalization ability, we scale up the training data to about 69 million high-quality frames, adopt a mixed image-video training strategy, upgrade the network architecture, and design better motion transformation and optimization objectives. Additionally, we discover that compact implicit keypoints can effectively represent a kind of blendshapes and meticulously propose a stitching and two retargeting modules, which utilize a small MLP with negligible computational overhead, to enhance the controllability. Experimental results demonstrate the efficacy of our framework even compared to diffusion-based methods. The generation speed remarkably reaches 12.8ms on an RTX 4090 GPU with PyTorch. The inference code and models are available at https://github.com/KwaiVGI/LivePortrait

cs.CV↗

arXiv2024

A Recursive Hybrid Tetrahedron Method for Brillouin-zone Integration

A recursive extension of the hybrid tetrahedron method for Brillouin-zone integration is proposed, allowing iterative tetrahedron refinement and significantly reducing the error from the linear tetrahedron method. The Brillouin-zone integral is expressed as a weighted sum on the initial grid, with integral weights collected recursively from the finest grid. Our method is capable of simultaneously handling multiple singularities in the integrand and thus may provide practical solutions to various Brillouin-zone integral tasks encountered in realistic calculations, including the computation of response and spectral function with superior sampling convergence. We demonstrate its effectiveness through numerical calculations of the density response functions of two model Hamiltonians and one real material system, the face-centered cubic cobalt.

cond-mat.mtrl-sci↗

arXiv2024

Berry phases in Coulomb drag of double-layer graphene system

Recent experiments suggest quantum interference effects in the Coulomb drag of double-layer graphene systems. By accounting for correlated interlayer impurity scattering under a weak magnetic field, our theoretical results reveal drag resistivities resembling those in weak (anti-)localization. It is established that the quantum interference effect is most significant when the chemical potentials match. The theory clarifies the roles of intra- and interlayer Berry phases in Coulomb drag in double-layer graphene systems and helps delineate the intra- and intervalley contributions. These insights are valuable for designing graphene-based electronic devices exploiting quantum effects.

cond-mat.mes-hall↗

arXiv2024

The Application of ChatGPT in Responding to Questions Related to the Boston Bowel Preparation Scale

Background: Colonoscopy, a crucial diagnostic tool in gastroenterology, depends heavily on superior bowel preparation. ChatGPT, a large language model with emergent intelligence which also exhibits potential in medical applications. This study aims to assess the accuracy and consistency of ChatGPT in using the Boston Bowel Preparation Scale (BBPS) for colonoscopy assessment. Methods: We retrospectively collected 233 colonoscopy images from 2020 to 2023. These images were evaluated using the BBPS by 3 senior endoscopists and 3 novice endoscopists. Additionally, ChatGPT also assessed these images, having been divided into three groups and undergone specific Fine-tuning. Consistency was evaluated through two rounds of testing. Results: In the initial round, ChatGPT's accuracy varied between 48.93% and 62.66%, trailing the endoscopists' accuracy of 76.68% to 77.83%. Kappa values for ChatGPT was between 0.52 and 0.53, compared to 0.75 to 0.87 for the endoscopists. Conclusion: While ChatGPT shows promise in bowel preparation scoring, it currently does not match the accuracy and consistency of experienced endoscopists. Future research should focus on in-depth Fine-tuning.

cs.AI↗

arXiv2023

Exploration of magnetoelastic deformations in spin-chain compound CuBr$_2$

We investigate a spin-$\frac{1}{2}$ antiferromagnet, CuBr$_2$, which has quasi-one-dimensional structural motifs. The system has previously been observed to exhibit unusual Raman modes possibly due to a locally deformed crystal structure driven by the low-dimensional magnetism. Using hard X-ray scattering and neutron total scattering, here we aim to verify a specific form of tetramerized lattice deformation proposed in the previous study. Apart from diffuse scattering signals which we can reproduce by performing a thorough modeling of the lattice's thermal vibrations, we do not observe evidence for a tetramerized lattice structure within our detection sensitivity. As a result, it is more likely that the unusual Raman modes in CuBr$_2$ arise from classical magnon-phonon hybridization, rather than from quantum spin-singlet-driven lattice deformation.

cond-mat.str-el↗

arXiv2023

MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification

Foundation models, often pre-trained with large-scale data, have achieved paramount success in jump-starting various vision and language applications. Recent advances further enable adapting foundation models in downstream tasks efficiently using only a few training samples, e.g., in-context learning. Yet, the application of such learning paradigms in medical image analysis remains scarce due to the shortage of publicly accessible data and benchmarks. In this paper, we aim at approaches adapting the foundation models for medical image classification and present a novel dataset and benchmark for the evaluation, i.e., examining the overall performance of accommodating the large-scale foundation models downstream on a set of diverse real-world clinical tasks. We collect five sets of medical imaging data from multiple institutes targeting a variety of real-world clinical tasks (22,349 images in total), i.e., thoracic diseases screening in X-rays, pathological lesion tissue screening, lesion detection in endoscopy images, neonatal jaundice evaluation, and diabetic retinopathy grading. Results of multiple baseline methods are demonstrated using the proposed dataset from both accuracy and cost-effective perspectives.

cs.CV↗

arXiv2022

An implementation of the density functional perturbation theory in the PAW framework

Quantifying materials' dynamical responses to external electromagnetic fields is central to understanding their physical properties. Here we present an implementation of the density functional perturbation theory for the computation of linear susceptibilities using the projector augmented-wave method. The Sternheimer equations are solved self-consistently through a nested iterative procedure to compute the first-order wavefunctions, from which the linear susceptibilities are obtained. As a demonstration, we compute the spin wave spectral functions of two magnetic metals. The computed magnon spectra for half-metallic CrO$_2$ and a Heusler intermetallic Cu$_2$MnAl show gapless Goldstone modes when spin rotation symmetry is preserved and display reasonable agreement with available experimental data. The Landau damping is computed to be small in CrO$_2$, but significant in Cu$_2$MnAl producing an asymmetric Lorentzian spectral lineshape. The access to linear susceptibilities as well as first-order wavefunctions offers a range of novel possibilities in quantitative understanding of materials' electronic properties from \textit{ab initio} methods.

cond-mat.mtrl-sci↗

arXiv2021

A silver(II) route to unconventional superconductivity

The highly unusual divalent silver in silver difluoride (AgF$_2$) features a nearly square lattice of Ag$^{+2}$ bridged by fluorides. As a structural and electronic analogue of cuprates, its superconducting properties are yet to be examined. Our first principles electronic structure calculations reveal a striking resemblance between AgF$_2$ and the cuprates. Computed spin susceptibility shows a magnetic instability consistent with the experimentally observed antiferromagnetic transition. A linearized Eliashberg theory in fluctuation-exchange approximation shows an unconventional singlet $d$-wave superconducting pairing for bulk AgF$_2$ at an optimal electron doping. The pairing is found to strengthen with a decreasing interlayer coupling, highlighting the importance of quasi-2D nature of the crystal structure. These findings place AgF$_2$ in the category of unconventional high-$T_\text{C}$ superconductors, and its chemical uniqueness may help shed new lights on the high-$T_\text{C}$ phenomena.

cond-mat.supr-con↗

arXiv2020

Zero-energy bound states in the high-temperature superconductors at the two-dimensional limit

Majorana zero modes (MZMs) that obey the non-Abelian statistics have been intensively investigated for potential applications in topological quantum computing. The prevailing signals in tunneling experiments "fingerprinting" the existence of MZMs are the zero-energy bound states (ZEBSs). However, nearly all of the previously reported ZEBSs showing signatures of the MZMs are observed in difficult-to-fabricate heterostructures at very low temperatures and additionally require applied magnetic field. Here, by using in-situ scanning tunneling spectroscopy, we detect the ZEBSs upon the interstitial Fe adatoms deposited on two different high-temperature superconducting one-unit-cell-thick iron chalcogenides on SrTiO3(001). The spectroscopic results resemble the phenomenological characteristics of the MZMs inside the vortex cores of topological superconductors. Our experimental findings may extend the MZM explorations in connate topological superconductors towards an applicable temperature regime and down to the two-dimensional limit. While a concrete understanding of the observations is lacking, possible explanations involving novel 2D superconducting states with spin-orbit coupling, spontaneous nucleation of anomalous vortices at the magnetic sites, and noncoplanar magnetic ordering may further stimulate theoretical understandings of the scarcely captured ZEBSs in strongly correlated systems with multiband Cooper pairing.

cond-mat.supr-con↗