In this demo, we present GenMatLab, a user-friendly web platform that makes latest AI techniques accessible for inverse materials design. The platform integrates data analysis and generative modeling into an easy-to-use interface, enabling researchers, material domain experts, and practitioners to explore and apply AI techniques without requiring advanced coding expertise. At its core are generative AI models that support interactive operations, allowing users to conduct inverse design and investigate generated candidates in an intuitive and exploratory way. By lowering technical barriers, GenMatLab empowers a broader community to leverage cutting-edge AI methods for accelerating materials discovery.

Fully Test-Time Adaptation (FTTA) addresses domain shifts without access to source data and training protocols of the pre-trained models. Traditional strategies that align source and target feature distributions are infeasible in FTTA due to the absence of training data and unpredictable target domains. In this work, we exploit a dual perspective on FTTA, and propose Agnostic FTTA (AFTTA) as a novel formulation that enables the usage of off-the-shelf domain transformations during test-time to enable direct generalization to unforeseeable target data. To address this, we develop an uncover-and-unlearn approach. First, we uncover potential unwanted shifts between source and target domains by simulating them through predefined mappings and consider them as nuisances. Then, during test-time prediction, the model is enforced to unlearn these nuisances by regularizing the consequent shifts in latent representations and label predictions. Specifically, a mutual information-based criterion is devised and applied to guide nuisances unlearning in the feature space and encourage confident and consistent prediction in label space. Our proposed approach explicitly addresses agnostic domain shifts, enabling superior model generalization under FTTA constraints. Extensive experiments on various tasks, involving corruption and style shifts, demonstrate that our method consistently outperforms existing approaches.

Generative AI (GenAI) has achieved remarkable success across a range of domains, but its capabilities remain constrained to statistical models of finite training sets and learning based on local gradient signals. This often results in artifacts that are more derivative than genuinely generative. In contrast, Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity, expanding generative capabilities by exploring uncharted solution spaces beyond the limits of available data. This work establishes a fundamental connection between EC and GenAI, redefining EC as Natural Generative AI (NatGenAI) – a generative paradigm governed by exploratory search under natural selection. We demonstrate that classical EC with parent-centric operators mirrors conventional GenAI, while disruptive operators enable structured evolutionary leaps, often within just a few generations, to generate out-of-distribution artifacts. Moreover, the methods of evolutionary multitasking provide an unparalleled means of integrating disruptive EC (with cross-domain recombination of evolved features) and moderated selection mechanisms (allowing novel solutions to survive), thereby fostering sustained innovation. By reframing EC as NatGenAI, we emphasize structured disruption and selection pressure moderation as essential drivers of creativity. This perspective extends the generative paradigm beyond conventional boundaries and positions EC as crucial to advancing exploratory design, innovation, scientific discovery, and open-ended generation in the GenAI era.

Grounding open-domain knowledge from large language models (LLMs) into real-world reinforcement learning (RL) tasks represents a transformative frontier in developing intelligent agents capable of advanced reasoning, adaptive planning, and robust decision-making in dynamic environments. In this paper, we introduce the LLM-RL Grounding Taxonomy, a systematic framework that categorizes emerging methods for integrating LLMs into RL systems by bridging their open-domain knowledge and reasoning capabilities with the task-specific dynamics, constraints, and objectives inherent to real-world RL environments. This taxonomy encompasses both training-free approaches, which leverage the zero-shot and few-shot generalization capabilities of LLMs without fine-tuning, and fine-tuning paradigms that adapt LLMs to environment-specific tasks for improved performance. We critically analyze these methodologies, highlight practical examples of effective knowledge grounding, and examine the challenges of alignment, generalization, and real-world deployment. Our work not only illustrates the potential of LLM-RL agents for enhanced decision-making, but also offers actionable insights for advancing the design of next-generation RL systems that integrate open-domain knowledge with adaptive learning.

In the field of Image-to-Image (I2I) translation, ensuring consistency between input images and their translated results is a key requirement for producing high-quality and desirable outputs. Previous I2I methods have relied on result consistency, which enforces consistency between the translated results and the ground truth output, to achieve this goal. However, result consistency is limited in its ability to handle complex and unseen attribute changes in translation tasks. To address this issue, we introduce a transition-aware approach to I2I translation, where the data translation mapping is explicitly parameterized with a transition variable, allowing for the modelling of unobserved translations triggered by unseen transitions. Furthermore, we propose the use of transition consistency, defined on the transition variable, to enable regularization of consistency on unobserved translations, which is omitted in previous works. Based on these insights, we present Unseen Transition Suss GAN (UTSGAN), a generative framework that constructs a manifold for the transition with a stochastic transition encoder and coherently regularizes and generalizes result consistency and transition consistency on both training and unobserved translations with tailor-designed constraints. Extensive experiments on four different I2I tasks performed on five different datasets demonstrate the efficacy of our proposed UTSGAN in performing consistent translations.

Most of the dimensionality reduction algorithms assume that data are independent and identically distributed (i.i.d.). In real-world applications, however, sometimes there exist relationships between data. Some relational learning methods have been proposed, but those with discriminative relationship analysis are lacking yet, as important supervisory information is usually ignored. In this paper, we propose a novel and general framework, called relational Fisher analysis (RFA), which successfully integrates relational information into the dimensionality reduction model. For nonlinear data representation learning, we adopt the kernel trick to RFA and propose the kernelized RFA (KRFA). In addition, the convergence of the RFA optimization algorithm is proved theoretically. By leveraging suitable strategies to construct the relational matrix, we conduct extensive experiments to demonstrate the superiority of our RFA and KRFA methods over related approaches.

This paper presents Dynamic-Aware GAN (DAGAN) as a data-efficient self-supervised paradigm for time-series data generation. To support sequential generation with sufficient clues of temporal dynamics, we explicitly model the transition dynamics within the data sequence through differencing, thus refining the vanilla sequence into one with inter-correlated triplets to characterize each time-step. This localized triplet consistent structure contributes to a self-supervision mechanism, which can provide more aspects of supervision for the overall stepwise dependencies encoded within the training data. Such a handy self-supervision mechanism is simple but can be beneficial especially when a model is presented with limited training data. Based on the insight, we present DAGAN which generalizes the locally regularized triplet consistency to distributional-level via dynamic encoding and joint distribution matching. Experiments on various synthetic and real-world datasets verify that our model achieves superior generation results with better quality and diversity compared with the state-of-the-art benchmarks, especially when the training data is scarce. Moreover, benefited from the dynamic-conditional and dynamic-consistent design, our DAGAN is capable of generating sequences that present specified dynamics.

In this paper, we revisit the Image-to-Image (I2I) translation problem with transition consistency, namely the consistency defined on the conditional data mapping between each data pairs. Explicitly parameterizing each data mappings with a transition variable $t$, i.e., $x \overset{t(x,y)}{\mapsto}y$, we discover that existing I2I translation models mainly focus on maintaining consistency on results, e.g., image reconstruction or attribute prediction, named result consistency in our paper. This restricts their generalization ability to generate satisfactory results with unseen transitions in the test phase. Consequently, we propose to enforce both result consistency and transition consistency for I2I translation, to benefit the problem with a closer consistency between the input and output. To benefit the generalization ability of the translation model, we propose transition encoding to facilitate explicit regularization of these two {kinds} of consistencies on unseen transitions. We further generalize such explicitly regularized consistencies to distribution-level, thus facilitating a generalized overall consistency for I2I translation problems. With the above design, our proposed model, named Transition Encoding GAN (TEGAN), can poss superb generalization ability to generate realistic and semantically consistent translation results with unseen transitions in the test phase. It also provides a unified understanding of the existing GAN-based I2I transition models with our explicitly modeling of the data mapping, i.e., transition. Experiments on four different I2I translation tasks demonstrate the efficacy and generality of TEGAN.

Multiview alignment, achieving one-to-one correspondence of multiview inputs, is critical in many real-world multiview applications, especially for cross-view data analysis problems. An increasing amount of work has studied this alignment problem with canonical correlation analysis (CCA). However, existing CCA models are prone to misalign the multiple views due to either the neglect of uncertainty or the inconsistent encoding of the multiple views. To tackle these two issues, this letter studies multiview alignment from a Bayesian perspective. Delving into the impairments of inconsistent encodings, we propose to recover correspondence of the multiview inputs by matching the marginalization of the joint distribution of multiview random variables under different forms of factorization. To realize our design, we present adversarial CCA (ACCA), which achieves consistent latent encodings by matching the marginalized latent encodings through the adversarial training paradigm. Our analysis, based on conditional mutual information, reveals that ACCA is flexible for handling implicit distributions. Extensive experiments on correlation analysis and cross-view generation under noisy input settings demonstrate the superiority of our model.

The shrinkage of cultivated land is a general trend in metropolitan areas. However, previous studies have mainly paid attention to the shrinkage of arable land in major grain-producing areas, mixed agro-pastoral areas, ecologically fragile areas and construction areas of major engineering projects (such as the Three Gorges project). This paper analyses the characteristics and driving factors of cultivated land change on the metropolitan area scale and longer time dimension. Exemplified by four metropolises in East Asia, Tokyo, Beijing, Shanghai and Guangzhou, based on official statistics for the cities involved, using correlation analysis, principal component analysis and regression analysis methods and Statistical Product and Service Solutions (SPSS) 25 software, the main driving factors and differences in cultivated land shrinkage in Beijing, Shanghai, Guangzhou and the Tokyo metropolitan area are quantitatively revealed. The results show the following: (1) there are some differences in the shrinkage in arable land and spatial distributions among different cities. Tokyo and Guangzhou still have some cultivated land in central urban areas, while there is no arable land in the central areas of Beijing and Shanghai. (2) There is a clear difference in the main driving factors of cultivated land shrinkage between the Tokyo metropolitan area and Beijing, Shanghai and Guangzhou. Residential area and population are the main driving factors for the former, while economic development and urbanisation are the main driving factors for the latter three areas. It shows that the shrinkage of cultivated land is closely related to the developmental stage of urbanisation. (3) There is a rather obvious difference in the main driving factors of cultivated land change among Beijing, Shanghai and Guangzhou. Gross Domestic Product (GDP) is the primary factor leading to the shrinkage of arable land in Beijing, built-up area is the primary factor in Shanghai, and the Engel’s coefficient for rural residents is the primary factor in Guangzhou. This reflects the difference in measures for the utilisation and protection of cultivated land among different cities. (4) The socioeconomic factors that affect the contraction of cultivated land are varied. In this study, industrial restructuring is included in the evaluation index system, mainly because industrial transformation and upgrading is essential for sustainable development of emerging global cities, and agricultural production conditions are not included in the evaluation index system, mainly because they are more the result of urbanisation than the cause.

Infrared target detection is essential for many computer vision tasks. Generally, the IR images present common infrared characteristics, such as poor texture information, low resolution, and high noise. However, these characteristics are ignored in the existing detection methods, making them fail in real-world scenarios. In this paper, we take infrared intensity into account and propose a novel backbone network named Deep-IRTarget. We first extract infrared intensity saliency by a convolution with a Gaussian kernel filtering the images in the frequency domain. We then propose the triple self-attention network to further extract spatial domain image saliency by selectively emphasize interdependent semantic features in each channel. Jointly exploiting infrared characteristics in the frequency domain and the overall semantic interdependencies in the spatial domain, the proposed Deep-IRTarget outperforms existing methods in real-world Infrared target detection tasks. Experimental results on two infrared imagery datasets demonstrate the superiorly of our model.

Canonical Correlation Analysis (CCA) is a classic technique for multi-view data analysis. To overcome the deficiency of linear correlation in practical multi-view learning tasks, various CCA variants were proposed to capture nonlinear dependency. However, it is non-trivial to have an in-principle understanding of these variants due to their inherent restrictive assumption on the data and latent code distributions. Although some works have studied probabilistic interpretation for CCA, these models still require the explicit form of the distributions to achieve a tractable solution for the inference. In this work, we study probabilistic interpretation for CCA based on implicit distributions. We present Conditional Mutual Information (CMI) as a new criterion for CCA to consider both linear and nonlinear dependency for arbitrarily distributed data. To eliminate direct estimation for CMI, in which explicit form of the distributions is still required, we derive an objective which can provide an estimation for CMI with efficient inference methods. To facilitate Bayesian inference of multi-view analysis, we propose Adversarial CCA (ACCA), which achieves consistent encoding for multi-view data with the consistent constraint imposed on the marginalization of the implicit posteriors. Such a model would achieve superiority in the alignment of the multi-view data with implicit distributions. It is interesting to note that most of the existing CCA variants can be connected with our proposed CCA model by assigning specific form for the posterior and likelihood distributions. Extensive experiments on nonlinear correlation analysis and cross-view generation on benchmark and real-world datasets demonstrate the superiority of our model.

Canonical Correlation Analysis (CCA) is a ubiquitous technique that shows promising performance in multi-view learning problems. Due to the conjugacy of the prior and the likelihood, probabilistic CCA (PCCA) presents the posterior with an analytic solution, which provides probabilistic interpretation for classic linear CCA. As the multi-view data are usually complex in practice, nonlinear mappings are adopted to capture nonlinear dependency among the views. However, the interpretation provided in PCCA cannot be generalized to this nonlinear setting, as the distribution assumptions on the prior and the likelihood makes it restrictive to capture nonlinear dependency. To overcome this bottleneck, in this paper, we provide a novel perspective for CCA based on implicit distributions. Specifically, we present minimum Conditional Mutual Information (CMI) as a new criteria to capture nonlinear dependency for multi-view learning problem. To eliminate the explicit distribution requirement in direct estimation of CMI, we derive an objective whose minimization implicitly leads to the proposed criteria. Based on this objective, we present an implicit probabilistic formulation for CCA, named Implicit CCA (ICCA), which provides a flexible framework to design CCA extensions with implicit distributions. As an instantiation, we present adversarial CCA (ACCA), a nonlinear CCA variant which benefits from consistent encoding achieved by adversarial learning. Quantitative correlation analysis and superior performance on cross-view generation task demonstrate the superiority of the proposed ACCA.

Label embedding plays an important role in many real-world applications. To enhance the label relatedness captured by the embeddings, multiple contexts can be adopted. However, these contexts are heterogeneous and often partially observed in practical tasks, imposing significant challenges to capture the overall relatedness among labels. In this paper, we propose a general Partial Heterogeneous Context Label Embedding (PHCLE) framework to address these challenges. Categorizing heterogeneous contexts into two groups, relational context and descriptive context, we design tailor-made matrix factorization formula to effectively exploit the label relatedness in each context. With a shared embedding principle across heterogeneous contexts, the label relatedness is selectively aligned in a shared space. Due to our elegant formulation, PHCLE overcomes the partial context problem and can nicely incorporate more contexts, which both cannot be tackled with existing multi-context label embedding methods. An effective alternative optimization algorithm is further derived to solve the sparse matrix factorization problem. Experimental results demonstrate that the label embeddings obtained with PHCLE achieve superb performance in image classification task and exhibit good interpretability in the downstream label similarity analysis and image understanding task.

Multi-output learning aims to simultaneously predict multiple outputs given an input. It is an important learning problem due to the pressing need for sophisticated decision making in real-world applications. Inspired by big data, the 4Vs characteristics of multi-output imposes a set of challenges to multi-output learning, in terms of the volume, velocity, variety and veracity of the outputs. Increasing number of works in the literature have been devoted to the study of multi-output learning and the development of novel approaches for addressing the challenges encountered. However, it lacks a comprehensive overview on different types of challenges of multi-output learning brought by the characteristics of the multiple outputs and the techniques proposed to overcome the challenges. This paper thus attempts to fill in this gap to provide a comprehensive review on this area. We first introduce different stages of the life cycle of the output labels. Then we present the paradigm on multi-output learning, including its myriads of output structures, definitions of its different sub-problems, model evaluation metrics and popular data repositories used in the study. Subsequently, we review a number of state-of-the-art multi-output learning methods, which are categorized based on the challenges.

Label embedding plays an important role in zero-shot learning. Side information such as attributes, semantic text representations, and label hierarchy are commonly used as the label embedding in zero-shot classification tasks. However, the label embedding used in former works considers either only one single context of the label, or multiple contexts without dependency. Therefore, different contexts of the label may not be well aligned in the embedding space to preserve the relatedness between labels, which will result in poor interpretability of the label embedding. In this paper, we propose a Multi-Context Label Embedding (MCLE) approach to incorporate multiple label contexts, e.g., label hierarchy and attributes, within a unified matrix factorization framework. To be specific, we model each single context by a matrix factorization formula and introduce a shared variable to capture the dependency among different contexts. Furthermore, we enforce sparsity constraint on our multi-context framework to strengthen the interpretability of the learned label embedding. Extensive experiments on two real-world datasets demonstrate the superiority of our MCLE in label description and zero-shot image classification.

In this paper, we propose a novel and general framework for dimensionality reduction, called Relational Fisher Analysis (RFA). Unlike traditional dimensionality reduction methods, such as linear discriminant analysis (LDA) and marginal Fisher analysis (MFA), RFA seamlessly integrates relational information among data into the representation learning framework, which in general provides strong evidence for related data to belong to the same class. To address nonlinear dimensionality reduction problems, we extend RFA to its kernel version. Furthermore, the convergence of RFA is also proved in this paper. Extensive experiments on documents understanding and recognition, face recognition and other applications from the UCI machine learning repository demonstrate the effectiveness and efficiency of RFA.

In this paper, we present a novel 3D object recognition system. In this system, we capture both the color and depth information of 3D objects using Kinect, and represent them in RGB-D images. To alleviate the deformations and partial defects of the obtained 3D surface textures, 3D texture reconstruction techniques are applied. In order to improve the recognition accuracy, we exploit metric learning methods for the K-nearest neighbor KNN classifier. Promising results are obtained on a real-world 3D object recognition application.

In recent years, many deep architectures have been proposed for handwritten text recognition. However, most of the previous deep models need large scale training data and a long training time to obtain good results. In this paper, we propose a novel deep learning method based on “stretching” the projection matrices of stacked feature learning models. We call the proposed method “stretching deep architectures” (or SDA). In the implementation of SDA, stacked feature learning models are first learned layer by layer, and then the stretching technique is applied on the weight matrices between successive layers. As the feature learning models can be efficiently optimized and the stretching results can be easily computed, the training of SDA is very fast and no back propagation is needed. We have tested SDA on handwritten digits recognition, Arabic subword recognition and English letter recognition tasks. Extensive experiments demonstrate that SDA performs not only better than shallow feature learning models, but also state-of-the-art deep learning models.