arXiv subjects

Binyu Zhao

Publications and source records attributed to Binyu Zhao.

8 recordsLinked to original sources

arXiv2026

Cosolvency response in polymer brushes

We present the first analytic theory with elegant and closed-form analytical solutions to explore the cosolvency effect in polymer brushes, where polymer chains that are poorly soluble in two pure solvents become fully soluble in certain mixtures thereof. This effect is key to designing stimulus-responsive smart materials but has not previously been addressed by analytic theory for polymer brushes. Our theoretical framework reveals that preferential adsorption of cosolvent induces an effective repulsion between monomers solvated by cosolvent and those solvated by solvent. The equilibrium solvation of polymer chains by cosolvent gives rise to a concentration-dependent $\chi$-function, which captures the effective interactions within the brush and reproduces the reentrant behavior characteristic of the cosolvency effect. The model predicts a discontinuous soluble transition followed by a re-collapse transition at higher cosolvent concentrations. Analytical treatment within a minimal free-energy model for the case of two symmetric poor solvents shows that the swelling and re-collapse transitions share the same thermodynamic origin. For low-density brushes, we derive an analytical approximation and delineate the phase diagram of parameter space in which discontinuous transitions occur. For cosolvency to take place, the theory specifies a minimum strength for preferential solvation and the associated repulsive coupling. Furthermore, it demonstrates that, contrary to previous models, repulsive interactions between cosolvent and solvent in the bulk are not required. This work lays the groundwork for the rational design of smart stimulus-responsive materials based on the cosolvency effect in polymer brushes, a capability which was not previously established.

cond-mat.soft↗

arXiv2026

Advancing Analytic Class-Incremental Learning through Vision-Language Calibration

Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often compromised by accumulated errors and feature incompatibility. In this paper, we first conduct a systematic study to dissect the failure modes of PTM-based analytic CIL, identifying representation rigidity as the primary bottleneck. Motivated by this insight, we propose VILA, a novel dual-branch framework that advances analytic CIL via a two-level vision-language calibration strategy. Specifically, we coherently fuse plastic, task-adapted features with a frozen, universal visual anchor at the feature level through geometric calibration, and leverage cross-modal semantic priors at the decision level to rectify prediction bias. This confluence maintains analytic-learning's extreme efficiency while overcoming its inherent brittleness. Extensive experiments across eight benchmarks demonstrate that VILA consistently yields superior performance, particularly in fine-grained and long-sequence scenarios. Our framework harmonizes high-fidelity prediction with the simplicity of analytic learning. Our code is available at https://github.com/byzhaoAI/VILA.

cs.LG↗

arXiv2025

MCE: Towards a General Framework for Handling Missing Modalities under Imbalanced Missing Rates

Multi-modal learning has made significant advances across diverse pattern recognition applications. However, handling missing modalities, especially under imbalanced missing rates, remains a major challenge. This imbalance triggers a vicious cycle: modalities with higher missing rates receive fewer updates, leading to inconsistent learning progress and representational degradation that further diminishes their contribution. Existing methods typically focus on global dataset-level balancing, often overlooking critical sample-level variations in modality utility and the underlying issue of degraded feature quality. We propose Modality Capability Enhancement (MCE) to tackle these limitations. MCE includes two synergistic components: i) Learning Capability Enhancement (LCE), which introduces multi-level factors to dynamically balance modality-specific learning progress, and ii) Representation Capability Enhancement (RCE), which improves feature semantics and robustness through subset prediction and cross-modal completion tasks. Comprehensive evaluations on four multi-modal benchmarks show that MCE consistently outperforms state-of-the-art methods under various missing configurations. The final published version is now available at https://doi.org/10.1016/j.patcog.2025.112591. Our code is available at https://github.com/byzhaoAI/MCE.

cs.CV↗

arXiv2025

Attributed Graph Clustering with Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning

This study introduces the Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning (MPCCL) model, a novel approach for attributed graph clustering that effectively bridges critical gaps in existing methods, including long-range dependency, feature collapse, and information loss. Traditional methods often struggle to capture high-order graph features due to their reliance on low-order attribute information, while contrastive learning techniques face limitations in feature diversity by overemphasizing local neighborhood structures. Similarly, conventional graph coarsening methods, though reducing graph scale, frequently lose fine-grained structural details. MPCCL addresses these challenges through an innovative multi-scale coarsening strategy, which progressively condenses the graph while prioritizing the merging of key edges based on global node similarity to preserve essential structural information. It further introduces a one-to-many contrastive learning paradigm, integrating node embeddings with augmented graph views and cluster centroids to enhance feature diversity, while mitigating feature masking issues caused by the accumulation of high-frequency node weights during multi-scale coarsening. By incorporating a graph reconstruction loss and KL divergence into its self-supervised learning framework, MPCCL ensures cross-scale consistency of node representations. Experimental evaluations reveal that MPCCL achieves a significant improvement in clustering performance, including a remarkable 15.24% increase in NMI on the ACM dataset and notable robust gains on smaller-scale datasets such as Citeseer, Cora and DBLP.

cs.LG↗

arXiv2025

GCL-GCN: Graphormer and Contrastive Learning Enhanced Attributed Graph Clustering Network

Attributed graph clustering holds significant importance in modern data analysis. However, due to the complexity of graph data and the heterogeneity of node attributes, leveraging graph information for clustering remains challenging. To address this, we propose a novel deep graph clustering model, GCL-GCN, specifically designed to address the limitations of existing models in capturing local dependencies and complex structures when dealing with sparse and heterogeneous graph data. GCL-GCN introduces an innovative Graphormer module that combines centrality encoding and spatial relationships, effectively capturing both global and local information between nodes, thereby enhancing the quality of node representations. Additionally, we propose a novel contrastive learning module that significantly enhances the discriminative power of feature representations. In the pre-training phase, this module increases feature distinction through contrastive learning on the original feature matrix, ensuring more identifiable initial representations for subsequent graph convolution and clustering tasks. Extensive experimental results on six datasets demonstrate that GCL-GCN outperforms 14 advanced methods in terms of clustering quality and robustness. Specifically, on the Cora dataset, it improves ACC, NMI, and ARI by 4.94%, 13.01%, and 10.97%, respectively, compared to the primary comparison method MBN.

cs.LG↗

arXiv2025

Tri-Learn Graph Fusion Network for Attributed Graph Clustering

In recent years, models based on Graph Convolutional Networks (GCN) have made significant strides in the field of graph data analysis. However, challenges such as over-smoothing and over-compression remain when handling large-scale and complex graph datasets, leading to a decline in clustering quality. Although the Graph Transformer architecture has mitigated some of these issues, its performance is still limited when processing heterogeneous graph data. To address these challenges, this study proposes a novel deep clustering framework that comprising GCN, Autoencoder (AE), and Graph Transformer, termed the Tri-Learn Graph Fusion Network (Tri-GFN). This framework enhances the differentiation and consistency of global and local information through a unique tri-learning mechanism and feature fusion enhancement strategy. The framework integrates GCN, AE, and Graph Transformer modules. These components are meticulously fused by a triple-channel enhancement module, which maximizes the use of both node attributes and topological structures, ensuring robust clustering representation. The tri-learning mechanism allows mutual learning among these modules, while the feature fusion strategy enables the model to capture complex relationships, yielding highly discriminative representations for graph clustering. It surpasses many state-of-the-art methods, achieving an accuracy improvement of approximately 0.87% on the ACM dataset, 14.14 % on the Reuters dataset, and 7.58 % on the USPS dataset. Due to its outstanding performance on the Reuters dataset, Tri-GFN can be applied to automatic news classification, topic retrieval, and related fields.

cs.LG↗

arXiv2023

BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalities

Collaborative perception enables agents to share complementary perceptual information with nearby agents. This would improve the perception performance and alleviate the issues of single-view perception, such as occlusion and sparsity. Most existing approaches mainly focus on single modality (especially LiDAR), and not fully exploit the superiority of multi-modal perception. We propose a collaborative perception paradigm, BM2CP, which employs LiDAR and camera to achieve efficient multi-modal perception. It utilizes LiDAR-guided modal fusion, cooperative depth generation and modality-guided intermediate fusion to acquire deep interactions among modalities of different agents, Moreover, it is capable to cope with the special case where one of the sensors, same or different type, of any agent is missing. Extensive experiments validate that our approach outperforms the state-of-the-art methods with 50X lower communication volumes in both simulated and real-world autonomous driving scenarios. Our code is available at https://github.com/byzhaoAI/BM2CP.

cs.CV↗

arXiv2022

How droplets dry on stretched soft substrates

Liquid droplets usually wet smooth and homogeneous substrates isotropically. Recent research works have revealed that droplets sit, slide and spread anisotropically on uniaxially stretched soft substrates, showing an enhanced wettability and contact line mobility along the stretching direction. This phenomenon arises from the anisotropic deformation of the substrate below the contact line. Here, we investigate how the stretching of soft substrates affects droplets drying. We observe that water droplet evaporates with an elongated non-circular contact line on the stretched substrates and switches the elongation direction during evaporation. The contact line velocity and its temporal evolution depend on the orientation of the contact line relative to the stretching direction. On the substrate stretched by 250%, the contact line recedes about 20% of the droplet lifetime earlier along the stretching direction and faster than its perpendicular direction. When nanoparticles are added into the liquid, the circular deposition pattern, i.e., the so-called coffee-ring, becomes elongated along the direction perpendicular to the stretching direction. Particularly, such non-circular deposition pattern exhibits periodic height gradients along its rim. The finer structure of the pattern can be controlled by applying different stretching ratios to the soft substrate and thus are correlated to the anisotropic surface stresses near the contact line.

cond-mat.soft↗