arXiv subjects

Tao You

Publications and source records attributed to Tao You.

12 recordsLinked to original sources

arXiv2026

Revisiting the hydromechanical formulation of a micromechanics-based phase-field model for poro-elastoplastic media

Even for tension-dominated fracture propagation, porous materials may deform plastically adjacent to the propagating fracture. As is common for porous materials, existing phase-field models typically employ a non-associative flow rule for plasticity, and a Helmholtz free energy based on strain and fluid pressure. This work revisits the hydromechanically coupled formulation of the phase-field model for fracture in poro-elastoplastic media by analyzing the strength surface and fracture driving force. Our analyses show that these common choices of flow rule and free energy will lead to a discontinuous strength surface across the tension-compression transition. A non-associative flow rule introduces a jump at the strength surface, while treating fluid pressure-rather than fluid content-as the independent variable in the Helmholtz free energy omits a coupling term from the phase-field driving force, also breaking continuity. Incorporating an associative Drucker-Prager flow rule and this omitted coupling term ensures a continuous strength surface and the accurate fracture driving force. The proposed model exhibits improved accuracy in hydromechanical responses when compared against the analytical solution of the Kristianovich-Geertsma-de Klerk hydraulic fracturing benchmark. Numerical simulations of hydraulic fracturing and biaxial compression in poro-elastoplastic media show that the model can reproduce both shear-dominated fractures induced by mechanical disturbance and tension-dominated fractures driven by fluid injection in saturated porous media.

cond-mat.soft↗

arXiv2026

A dual--continuum phase-field model for hydraulic fracturing: Viscosity-dominated regime and fluid lag

The phase-field model regularizes sharp fractures into a diffuse representation, blurring the boundary between the fracture and the intact material. This blurring makes it difficult to capture distinct domain processes in hydraulic fracturing, where Reynolds flow governs the fracture and Darcy flow describes the surrounding porous matrix. Consequently, the blurred delineation artificially smears the pressure field across the fracture--matrix interface, which is acceptable in toughness-dominated hydraulic fracturing regimes where pressure drops within the fracture are negligible. However, in viscosity-dominated regimes, typically for actual subsurface injections due to high injection rates, the fluid pressure drops more drastically, and the fluid front may even lag behind the propagating fracture tip, a phenomenon that a smeared pressure field cannot capture. Despite its relevance, the viscosity-dominated regime has not been addressed by any existing phase-field models to date, likely due to its numerical instability. In this study, we propose a dual--continuum phase-field model based on double-porosity microporomechanics that explicitly separates mesoscale crack pressure from micropore pressure. The framework provides a variationally consistent formulation alongside phase-field--dependent poroelasticity. To ensure the numerical stability of the hydromechanical coupling, a fixed-stress split scheme is modified for two independent fluid pressures, while a variational inequality constraint is applied to reproduce fluid lag. Verified against the closed-form solutions in toughness-dominated, viscosity-dominated, and early-time transitional regimes, the model accurately captures complex fluid flow behavior and transient fluid lag within the fracture, and opens a new frontier for applying phase-field models to realistic viscosity-dominated hydraulic fracturing.

physics.flu-dyn↗

arXiv2024

A phase-field fracture model in thermo-poro-elastic media with micromechanical strain energy degradation

This work extends the hydro-mechanical phase-field fracture model to non-isothermal conditions with micromechanics based poroelasticity, which degrades Biot's coefficient not only with the phase-field variable (damage) but also with the energy decomposition scheme. Furthermore, we propose a new approach to update porosity solely determined by the strain change rather than damage evolution as in the existing models. As such, these poroelastic behaviors of Biot's coefficient and the porosity dictate Biot's modulus and the thermal expansion coefficient. For numerical implementation, we employ an isotropic diffusion method to stabilize the advection-dominated heat flux and adapt the fixed stress split method to account for the thermal stress. We verify our model against a series of analytical solutions such as Terzaghi's consolidation, thermal consolidation, and the plane strain hydraulic fracture propagation, known as the KGD fracture. Finally, numerical experiments demonstrate the effectiveness of the stabilization method and intricate thermo-hydro-mechanical interactions during hydraulic fracturing with and without a pre-existing weak interface.

math.NA↗

arXiv2024

DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction

Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions. In recent studies, denoising diffusion models have shown more promising in unifying task frameworks owing to their inherent ability of generalization. Following this motivation, a novel Diffusion architecture for generalized audio-visual Saliency prediction (DiffSal) is proposed in this work, which formulates the prediction problem as a conditional generative task of the saliency map by utilizing input audio and video as the conditions. Based on the spatio-temporal audio-visual features, an extra network Saliency-UNet is designed to perform multi-modal attention modulation for progressive refinement of the ground-truth saliency map from the noisy map. Extensive experiments demonstrate that the proposed DiffSal can achieve excellent performance across six challenging audio-visual benchmarks, with an average relative improvement of 6.3\% over the previous state-of-the-art results by six metrics.

cs.CV↗

arXiv2024

LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery

Visual question answering (VQA) is crucial for promoting surgical education. In practice, the needs of trainees are constantly evolving, such as learning more surgical types, adapting to different robots, and learning new surgical instruments and techniques for various surgeries. However, patient data privacy often restricts the availability of old data when updating the model, necessitating an exemplar-free continual learning (CL) setup. Prior CL studies overlooked two vital problems in the surgical domain: 1) large domain shifts from diverse surgical operations collected from multiple sources, and 2) severe data imbalance arising from the uneven presence of surgical instruments or activities. This paper proposes addressing these problems with a multimodal large language model (LLM) and an adaptive weight assignment methodology. We first develop a new multi-teacher CL framework that leverages a multimodal LLM as the additional teacher. The strong generalization ability of the LLM can bridge the knowledge gap when domain shifts and data imbalances occur. We then put forth a novel data processing method that transforms complex LLM embeddings into logits compatible with our CL framework. We further design an adaptive weight assignment approach that balances the generalization ability of the LLM and the domain expertise of the old CL model. Finally, to comprehensively test the effectiveness of our proposed method, we have also constructed two new surgical VQA datasets that are largely different from existing ones and could be valuable resources for future research. Extensive experimental results on the tested datasets demonstrate the superiority of our method to other advanced CL schemes.

cs.IR↗

arXiv2023

UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection

Video saliency prediction and detection are thriving research domains that enable computers to simulate the distribution of visual attention akin to how humans perceiving dynamic scenes. While many approaches have crafted task-specific training paradigms for either video saliency prediction or video salient object detection tasks, few attention has been devoted to devising a generalized saliency modeling framework that seamlessly bridges both these distinct tasks. In this study, we introduce the Unified Saliency Transformer (UniST) framework, which comprehensively utilizes the essential attributes of video saliency prediction and video salient object detection. In addition to extracting representations of frame sequences, a saliency-aware transformer is designed to learn the spatio-temporal representations at progressively increased resolutions, while incorporating effective cross-scale saliency information to produce a robust representation. Furthermore, a task-specific decoder is proposed to perform the final prediction for each task. To the best of our knowledge, this is the first work that explores designing a transformer structure for both saliency modeling tasks. Convincible experiments demonstrate that the proposed UniST achieves superior performance across seven challenging benchmarks for two tasks, and significantly outperforms the other state-of-the-art methods.

cs.CV↗

arXiv2023

Accurate Prediction of Antibody Function and Structure Using Bio-Inspired Antibody Language Model

In recent decades, antibodies have emerged as indispensable therapeutics for combating diseases, particularly viral infections. However, their development has been hindered by limited structural information and labor-intensive engineering processes. Fortunately, significant advancements in deep learning methods have facilitated the precise prediction of protein structure and function by leveraging co-evolution information from homologous proteins. Despite these advances, predicting the conformation of antibodies remains challenging due to their unique evolution and the high flexibility of their antigen-binding regions. Here, to address this challenge, we present the Bio-inspired Antibody Language Model (BALM). This model is trained on a vast dataset comprising 336 million 40% non-redundant unlabeled antibody sequences, capturing both unique and conserved properties specific to antibodies. Notably, BALM showcases exceptional performance across four antigen-binding prediction tasks. Moreover, we introduce BALMFold, an end-to-end method derived from BALM, capable of swiftly predicting full atomic antibody structures from individual sequences. Remarkably, BALMFold outperforms those well-established methods like AlphaFold2, IgFold, ESMFold, and OmegaFold in the antibody benchmark, demonstrating significant potential to advance innovative engineering and streamline therapeutic antibody development by reducing the need for unnecessary trials.

q-bio.BM↗

arXiv2023

Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization

Self-supervised sound source localization is usually challenged by the modality inconsistency. In recent studies, contrastive learning based strategies have shown promising to establish such a consistent correspondence between audio and sound sources in visual scenarios. Unfortunately, the insufficient attention to the heterogeneity influence in the different modality features still limits this scheme to be further improved, which also becomes the motivation of our work. In this study, an Induction Network is proposed to bridge the modality gap more effectively. By decoupling the gradients of visual and audio modalities, the discriminative visual representations of sound sources can be learned with the designed Induction Vector in a bootstrap manner, which also enables the audio modality to be aligned with the visual modality consistently. In addition to a visual weighted contrastive loss, an adaptive threshold selection strategy is introduced to enhance the robustness of the Induction Network. Substantial experiments conducted on SoundNet-Flickr and VGG-Sound Source datasets have demonstrated a superior performance compared to other state-of-the-art works in different challenging scenarios. The code is available at https://github.com/Tahy1/AVIN

cs.CV↗

arXiv2023

On poroelastic strain energy degradation in the variational phase--field models for hydraulic fracture

Though a number of formulations have been proposed for phase--field models for hydraulic fracture, the definition of the degraded poroelastic strain energy varies from one model to another. This study explores previously proposed forms of the poroelastic strain energy with diffused fracture and assesses their ability to recover the explicit fracture opening aperture. We then propose a new form of degraded poroelastic strain energy derived from micromechanical analyses. Unlike the previously proposed models, our poroelastic strain energy degradation depends not only on the phase--field variable (damage) but also on the type of strain energy decomposition. Comparisons against closed form solutions suggest that our proposed model can recover crack opening displacement more accurately irrespective of Biot's coefficient or the pore--pressure distribution. We then verify our model against the plane strain hydraulic fracture propagation, known as the KGD fracture, in the toughness dominated regime. Finally, we demonstrate the model's ability to handle complex hydraulic fracture interactions with a pre--existing natural fracture.

math.NA↗

arXiv2022

Selective clustering ensemble based on kappa and F-score

Clustering ensemble has an impressive performance in improving the accuracy and robustness of partition results and has received much attention in recent years. Selective clustering ensemble (SCE) can further improve the ensemble performance by selecting base partitions or clusters in according to diversity and stability. However, there is a conflict between diversity and stability, and how to make the trade-off between the two is challenging. The key here is how to evaluate the quality of the base partitions and clusters. In this paper, we propose a new evaluation method for partitions and clusters using kappa and F-score, leading to a new SCE method, which uses kappa to select informative base partitions and uses F-score to weight clusters based on stability. The effectiveness and efficiency of the proposed method is empirically validated over real datasets.

cs.LG↗

arXiv2022

Regularity based spectral clustering and mapping the Fiedler-carpet

Spectral clustering is discussed from many perspectives, by extending it to rectangular arrays and discrepancy minimization too. Near optimal clusters are obtained with singular value decomposition and with the weighted $k$-means algorithm. In case of rectangular arrays, this means enhancing the method of correspondence analysis with clustering, and in case of edge-weighted graphs, a normalized Laplacian based clustering. In the latter case it is proved that a spectral gap between the $(k-1)$th and $k$th smallest positive eigenvalues of the normalized Laplacian matrix gives rise to a sudden decrease of the inner cluster variances when the number of clusters of the vertex representatives is $2^{k-1}$, but only the first $k-1$ eigenvectors, constituting the so-called Fiedler-carpet, are used in the representation. Application to directed migration graphs is also discussed.

math.CO↗

arXiv2016

Community Detection in Complex Networks Using Density-based Clustering Algorithm

Like clustering analysis, community detection aims at assigning nodes in a network into different communities. Fdp is a recently proposed density-based clustering algorithm which does not need the number of clusters as prior input and the result is insensitive to its parameter. However, Fdp cannot be directly applied to community detection due to its inability to recognize the community centers in the network. To solve the problem, a new community detection method (named IsoFdp) is proposed in this paper. First, we use Isomap technique to map the network data into a low dimensional manifold which can reveal diverse pair-wised similarity. Then Fdp is applied to detect the communities in networks. An improved partition density function is proposed to select the proper number of communities automatically. We test our method on both synthetic and real-world networks, and the results demonstrate the effectiveness of our algorithm over the state-of-the-art methods.

cs.SI↗