Institution profile

Anhui University

Academic institutionasia · cn
Official website
Research library367linked papers
Opportunities0open roles
Selected work

Representative Papers

Instruction-Driven 3D Facial Expression Generation and Transition

Jan 13, 2026IEEE transactions on multimedia

This work addresses the limitation of existing methods that typically support only six basic 3D facial expressions, hindering fine-grained and semantically driven generation and transitions. To overcome this, the authors propose the I2FET framework, which enables text-driven synthesis of arbitrary 3D facial expressions and smooth transitions between them. The key innovations include an IFED module for multimodal alignment between textual instructions and facial expression features, and a vertex reconstruction loss to enhance semantic consistency in the latent space. Evaluated on the CK+ and CelebV-HQ datasets, the proposed method significantly outperforms current approaches, generating high-fidelity, semantically accurate, and naturally continuous 3D facial expression sequences.

1 citationsRead paper

Efficient Training of Neural Fractional-Order Differential Equation via Adjoint Backpropagation

Mar 20, 2025

To address the high memory consumption and computational complexity arising from forward-mode differentiation in training Neural Fractional Differential Equations (Neural FDEs), this work introduces, for the first time, adjoint-based backpropagation into the Neural FDE training framework. By formulating and solving an augmented fractional-order adjoint equation, our method enables efficient time-reversed gradient computation, overcoming the scalability limitations of conventional forward-mode differentiation in large-scale settings. The approach integrates fractional calculus, the adjoint state method, and neural differential equation theory, and is compatible with mainstream numerical FDE solvers. Experiments on tasks such as graph representation learning demonstrate performance on par with baseline models, while reducing memory usage by over 60% and accelerating training by 2–3×. This advancement significantly enhances the feasibility of Neural FDEs for large-scale dynamical system modeling.

1 citationsRead paper

High-Order Matching for One-Step Shortcut Diffusion Models

Feb 02, 2025

First-order single-step diffusion models, which model only velocity, produce trajectories with poor smoothness and geometric alignment—especially in high-curvature regions. To address this, we propose the first distributional transport framework incorporating higher-order kinematics (acceleration and jerk), explicitly integrating higher-order time derivatives into single-step diffusion modeling to theoretically guarantee superior approximation accuracy. Our method synergistically combines higher-order dynamics matching, manifold-aware distribution transport, and convergence analysis, thereby enhancing trajectory smoothness, generation stability, and fidelity to underlying data manifold geometry. Experiments on high-curvature image generation tasks demonstrate that our approach significantly outperforms existing baselines: generated trajectories are markedly smoother, and distribution alignment is substantially more precise. This work establishes a new benchmark for single-step diffusion modeling.

1 citationsRead paper

TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation

May 06, 2024arXiv.org

To address weak generalization caused by uniform sample training and limited representation capacity due to shared single supervision across multiple encoders in CTR prediction, this paper proposes TF4CTR—a dual-focus framework. Methodologically, it introduces (1) a Sample Selection Embedding Module (SSEM) that enables difficulty-aware sample selection and dynamic encoder assignment; (2) a Dual-Focus Loss (TF Loss) providing hierarchical, sample-level differentiated supervision; and (3) a Dynamic Fusion Module (DFM) enhancing multi-granularity feature interaction modeling. The framework is plug-and-play compatible with existing architectures. Extensive experiments on five real-world datasets demonstrate consistent and significant performance gains over mainstream models—including Wide&Deep, DeepFM, and AutoInt—validating its strong compatibility and superior generalization capability. Code and experimental logs are publicly available.

1 citationsRead paper
Recent publications

Latest Papers