Blind image quality assessment (BIQA) methods often incorporate auxiliary tasks to improve performance. However, existing approaches face limitations due to insufficient integration and a lack of flexible uncertainty estimation, leading to suboptimal performance. To address these challenges, we propose a multitasks-based Deep Evidential Fusion Network (DEFNet) for BIQA, which performs multitask optimization with the assistance of scene and distortion type classification tasks. To achieve a more robust and reliable representation, we design a novel trustworthy information fusion strategy. It first combines diverse features and patterns across sub-regions to enhance information richness, and then performs local-global information fusion by balancing fine-grained details with coarse-grained context. Moreover, DEFNet exploits advanced uncertainty estimation technique inspired by evidential learning with the help of normal-inverse gamma distribution mixture. Extensive experiments on both synthetic and authentic distortion datasets demonstrate the effectiveness and robustness of the proposed framework. Additional evaluation and analysis are carried out to highlight its strong generalization capability and adaptability to previously unseen scenarios.

Molecular assembly (MA) has long been a fundamental task in chemistry and biology, with the potential to create new materials and enable novel functions beyond the molecular scale. However, its vast conformational search space poses substantial challenges, and current generative models remain limited in capturing molecular flexibility and preventing non-physical poses. In this paper, we propose AssemUDB, a diffusion bridge–based framework that learns transport mappings between two distinct flexible domains for molecular assembly generation. We reformulate the marginal matching constraint of diffusion bridges as a coupling distribution governed by unbalanced transport rather than imposing strict conservation. Subsequently, we employ a progressive process from structural relaxation in Euclidean space to assembly on the SE(3) manifold. This relaxation of marginal conservation grants the generative model greater flexibility and leads to more physically plausible atom placements. Comprehensive experiments demonstrate the superior performance of AssemUDB. Notably, we find that the method demonstrates performance comparable to, or even better than, mature tools such as PackMol for packing tasks.

Coarse-grained (CG) molecular dynamics of proteins is a preferred approach to studying large molecules on extended time scales by condensing the entire atomic model into a limited number of pseudo-atoms and preserving the thermodynamic properties of the system. However, the significantly increased efficiency impedes the analysis of substantial physicochemical information, since high-resolution atomic details are sacrificed to accelerate simulation. In this paper, we propose LatCPB, a generative approach based on diffusion that enables high-resolution backmapping of CG proteins. Specifically, our model encodes an all-atom into discrete latent embeddings, aligned with learnable multimodal discrete priors for circumventing posterior collapse and maintaining the discrete properties of the protein sequence. During the generation, we further design a latent diffusion process within the continuous latent space due to the potential stochastics in the data. Moreover, LatCPB performs a contrastive learning strategy in latent space to separate feature representations of various molecules and conformations of the same molecule, thus enhancing the comprehension of molecular representational diversity. Experimental results demonstrate that LatCPB is able to backmap CG proteins effectively and achieve outstanding performance.

Molecular synthetic space projecting is a critical technique in de novo molecular design, which aims to rectify molecules without synthesizability guarantee by converting them into synthetic postfix notations. However, the vast synthesizable chemical space and the discrete data modalities involved pose significant challenges to postfix notation conversion benchmarking. In this paper, we exploit conditional probability transitions in discrete state space and introduce MoleBridge, a deep generative model built on the Markov bridge approach for designing postfix notations of molecular synthesis pathways. MoleBridge consists of two iterative optimizations: i) Autoregressive extending of notation tokens from molecular graphs, and ii) generation of discrete reaction postfix notations through Markov bridge, where noisy token blocks are progressively denoised over multi-step iterations. For the challenging second iteration, which demands sensitivity to incorrect generative probability paths within intricate chemical spaces, we employ a thinking and denoising separation approach to denoise. Empirically, we find that MoleBridge is capable of accurately predicting synthesis pathways while exhibiting excellent performance in a variety of application scenarios.

Complementarity determining region (CDR) is a specific region in antibody molecules that binds to antigens, where a small portion of residues undergoes particularly pronounced variations. Generating CDRs with high affinity and specificity is a pivotal milestone in accelerating drug development for daunting and unresolved diseases. However, existing approaches predominantly center on characterizing the attributes of residues through sequential generation models, thus falling short in effectively modeling the intricate spatial correlations among residues and frequently succumbing to the trap of generating sequences that exhibit a high degree of arbitrariness. In this article, we propose a novel synergistic attention-guided cascaded graph diffusion model, termed GraphCas, which offers a pathway for optimized generation of high-affinity CDRs. Our approach is the first cascaded-based graph diffusion model for CDR synthesis. Specifically, we design a graph propagation algorithm with a relation-aware synergistic attention mechanism, enabling the targeted acquisition of structural insights from diverse protein sequences and bolstering the global information representation of the graph by precisely localizing to long-range key residue sites. We design a cascaded conditional enhanced diffusion approach, providing the capability to incorporate additional control constraints into the input. Experimental results demonstrate that GraphCas can generate photo-realistic CDRs and achieve performance comparable to top-tier approaches. In particular, GraphCas reduces the RMSD by nearly 0.42 units in the H1 region and improves the ERRAT by 9.36% points in the L1 region.

The actual collection of tabular data for sharing involves confidentiality and privacy constraints, leaving the potential risks of machine learning for interventional data analysis unsafely averted. Synthetic data has emerged recently as a privacy-protecting solution to address this challenge. However, existing approaches regard discrete and continuous modal features as separate entities, thus falling short in properly capturing their inherent correlations. In this paper, we propose a novel contrastive learning guided Gaussian Transformer autoencoder, termed GTCoder, to synthesize photo-realistic multimodal tabular data for scientific research. Our approach introduces a transformer-based fusion module that seamlessly integrates multimodal features, permitting for mining more informative latent representations. The attention within the fusion module directs the integrated output features to focus on critical components that facilitate the task of generating latent embeddings. Moreover, we formulate a contrastive learning strategy to implicitly constrain the embeddings from discrete features in the latent feature space by encouraging the similar discrete feature distributions closer while pushing the dissimilar further away, in order to better enhance the representation of the latent embedding. Experimental results indicate that GTCoder is effective to generate photo-realistic synthetic data, with interactive interpretation of latent embedding, and performs favorably against some baselines on most real-world and simulated datasets.

Magnetic resonance (MR) image quality assessment plays a crucial role in disease diagnosis and data analysis. Existing methods typically treat the data as images and process them with convolutional networks, thereby ignoring the sequential characteristics of MR data. In this paper, we propose a hybrid spatial-frequency network (HSFNet) for MR image quality assessment, which extracts MR image quality features in both spatial and frequency domains. Specifically, within each data domain, information from local images and global sequences is iteratively integrated by applying a Mamba-based cascading processing module for multiple times. Extensive experiments on both T1-weighting and T2-weighting MR datasets demonstrate the proposed method’s effectiveness and generalization ability in comparison with state-of-the-art MR image quality assessment methods.

Parameter-efficient transfer learning (PETL) methods show promise in adapting a pre-trained model to various downstream tasks while training only a few parameters. In the computer vision (CV) domain, numerous PETL algorithms have been proposed, but their direct employment or comparison remains inconvenient. To address this challenge, we construct a Unified Visual PETL Benchmark (V-PETL Bench) for the CV domain by selecting 30 diverse, challenging, and comprehensive datasets from image recognition, video action recognition, and dense prediction tasks. On these datasets, we systematically evaluate 25 dominant PETL algorithms and open-source a modular and extensible codebase for fair evaluation of these algorithms. V-PETL Bench runs on NVIDIA A800 GPUs and requires approximately 310 GPU days. We release all the benchmark, making it more efficient and friendly to researchers. Additionally, V-PETL Bench will be continuously updated for new PETL algorithms and CV tasks.

This paper studies the extended state observer (ESO)-based distributed model predictive control (DMPC) approach to deal with multiple mobile robot formation with unknown disturbances. The distributed control problem with path parameters synchronization and disturbance rejection is formulated for formation system according to the tracking error dynamic model, where the reference paths are parameterized. A local distributed controller is designed by using DMPC strategy for each mobile robot in the absence of disturbance by including parameter synchronization constraints in the quadratic performance index as coupling terms. The DMPC optimization problem is solved by using Nash-optimization iteration strategy with the maximum number of iteration constraint. To improve the ability of anti-jamming, a feedforward compensation controller is designed by using ESO method, where the ESO is designed by pole assignment. The convergence of the proposed iterative algorithm is given. Furthermore, the input-to-state stability property of the proposed composite controller, combining a feedforward compensation controller and local distributed controller, is analyzed for the closed-loop system. Finally, the validity of the proposed algorithm is verified by two simulation examples.