Explore the vast range of titles available.

Large‐scale artificial intelligence (AI) models can mine potential patterns from massive amounts of data and provide more accurate analyses. This capability has enabled its gradual application in various areas of bioinformatics. However, few reviews have comprehensively summarized the applications of different types of large‐scale AI models in key areas of bioinformatics. Therefore, we first introduce the concept of large‐scale AI models and classify them into three types. Second, we summarize the key methods, applications, and resources of these three types of bioinformatics models. Finally, we discuss challenges and directions for future research. This review provides researchers with a comprehensive perspective to better understand the applications of large‐scale AI models in bioinformatics.

We introduce a novel simulated certainty equivalent approximation (SCEQ) method for solving dynamic stochastic problems. Our examples show that SCEQ can quickly solve high-dimensional finite- or infinite-horizon, stationary or non- stationary dynamic stochastic problems with hundreds of state variables, a wide state space, and occasionally binding constraints. With the SCEQ method, a desk- top computer will suffice for large problems, but it can also use parallel tools ef- ficiently. The SCEQ method is simple, stable, and can utilize any solver, making it suitable for solving complex economic problems that cannot be solved by other algorithms.

Characterizing the impact of human actions on terrestrial water fluxes and storages at multi‐basin, continental, and global scales has long been on the agenda of scientists engaged in climate science, hydrology, and water resources systems analysis. This need has resulted in a variety of modeling efforts focused on the representation of water infrastructure operations. Yet, the representation of human‐water interactions in large‐scale hydrological models is still relatively crude, fragmented across models, and often achieved at coarse resolutions (∼${\\sim} $ 10–100 km) that cannot capture local water management decisions. In this commentary, we argue that the concomitance of four drivers and innovations is poised to change the status quo: “hyper‐resolution” hydrological models (∼${\\sim} $ 0.1–1 km), multi‐sector modeling, satellite missions able to monitor the outcome of human actions, and machine learning are creating a fertile environment for human‐water research to flourish. We then outline four challenges that chart future research in hydrological modeling: (a) creating hyper‐resolution global data sets of water management practices, (b) improving the characterization of anthropogenic interventions on water quantity, stream temperature, and sediment transport, (c) improving model calibration and diagnostic evaluation, and (d) reducing the computational requirements associated with the successful exploration of these challenges. Overcoming them will require addressing modeling, computational, and data development needs that cut across the hydrology community, thereby requiring a major communal effort.

Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on heavy and repetitive training cost which impedes their practical deployment. In this paper, we propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network. We achieve this remarkable speed by devising a new network that directly constructs a 3D triplane from a text prompt. The core innovation of our Instant3D lies in our exploration of strategies to effectively inject text conditions into the network. In particular, we propose to combine three key mechanisms: cross-attention, style injection, and token-to-plane transformation, which collectively ensure precise alignment of the output with the input text. Furthermore, we propose a simple yet effective activation function, the scaled-sigmoid, to replace the original sigmoid function, which speeds up the training convergence by more than ten times. Finally, to address the Janus (multi-head) problem in 3D generation, we propose an adaptive Perp-Neg algorithm that can dynamically adjust its concept negation scales according to the severity of the Janus problem during training, effectively reducing the multi-head effect. Extensive experiments on a wide variety of benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods both qualitatively and quantitatively, while achieving significantly better efficiency. The code, data, and models are available at https://ming1993li.github.io/Instant3DProj/.

Large‐scale hydrodynamic models are vital for flood risk assessment and understanding the global water cycle; however, their results can include uncertainties related to spatial resolution. Few studies have evaluated hydrodynamic models across a range of spatial resolutions, with most focusing on a few variables (e.g., discharge) and often neglecting performance at ungauged sites or the role of parameter optimization. We addressed these limitations by comparing Catchment‐based Macro‐scale Floodplain (CaMa‐Flood) model simulations in the Amazon River basin at different spatial resolutions, using the higher resolution as a benchmark in each comparison. We found good inter‐resolution performance in simulating discharge and water depth, with coefficients of determination exceeding 0.88 in >80% of locations. The normalized Nash–Sutcliffe efficiencies for discharge and water depth were greater than 0.83 and 0.68, respectively, in more than 75% of locations, suggesting that most locations had consistent hydrodynamics. We detected large discrepancies in discharge between simulations at ∼2.5% of locations due to limited representation of bifurcation flow, floodplain conveyance, and backwater at river confluences in the model. Water depth also differed significantly at ∼3% of locations, mainly at headwaters, due to width bottleneck sections. Flood extent patterns differed minimally between simulations around the main stream and large sub‐streams, whereas improvements in the downscaling method are required for small sub‐streams. Our results demonstrate the need to improve the representation of bifurcation channels and floodplain parameterization for specific locations, although the general river hydrodynamics patterns were well‐captured by computationally efficient moderate‐resolution (i.e., 6 arcmin) CaMa‐Flood simulations. Plain Language Summary Large‐scale models that predict how water moves are crucial for assessing flood risks and understanding the global water cycle. However, these models can have uncertainties related to their spatial resolution. Few studies have evaluated these models at different levels of detail but usually focused on a few variables or ignored areas without data and parameter adjustments. To address these gaps, we compared the Catchment‐based Macro‐scale Floodplain (CaMa‐Flood) model's simulations of the Amazon River at different resolutions, using the highest level of detail as a reference. The model simulated flow and depth at lower resolutions, achieving a strong agreement with higher resolutions at 80%–90% of locations. Most locations showed consistent results for flow and depth. Still, there were significant differences in a small percentage of areas due to the model's limited ability to represent complex flow patterns and certain channel features such as bifurcation flow, backwater effect, floodplain conveyance, and bottleneck channels, across various resolutions. Flood extent patterns were generally similar between simulations, but improvements are needed for smaller streams. Our findings highlight the need to enhance the model's representation by improving baseline river network data, although overall, the model's moderate‐resolution simulations effectively captured general river hydrodynamics. Key Points Sub‐grid parameterization makes moderate‐resolution (6 arcmin) simulation results almost similar to those at higher resolution Causes of differences in simulated hydrodynamics in a few locations are attributed to the characteristics of river models' physics Better sub‐grid topography treatment (bifurcation, river confluence, channel width) would potentially enhance low‐resolution simulations

Virtual try-on focuses on adjusting the given clothes to fit a specific person seamlessly while avoiding any distortion of the patterns and textures of the garment. However, the clothing identity uncontrollability and training inefficiency of existing diffusion-based methods, which struggle to maintain the identity even with full parameter training, are significant limitations that hinder the widespread applications. In this work, we propose an effective and efficient framework, termed TryOn-Adapter. Specifically, we first decouple clothing identity into fine-grained factors: style for color and category information, texture for high-frequency details, and structure for smooth spatial adaptive transformation. Our approach utilizes a pre-trained exemplar-based diffusion model as the fundamental network, whose parameters are frozen except for the attention layers. We then customize three lightweight modules (Style Preserving, Texture Highlighting, and Structure Adapting) incorporated with fine-tuning techniques to enable precise and efficient identity control. Meanwhile, we introduce the training-free T-RePaint strategy to further enhance clothing identity preservation while maintaining the realistic try-on effect during the inference. Our experiments demonstrate that our approach achieves state-of-the-art performance on two widely-used benchmarks. Additionally, compared with recent full-tuning diffusion-based methods, we only use about half of their tunable parameters during training. The code will be made publicly available at https://github.com/jiazheng-xing/TryOn-Adapter .

The loess structural planes of different formation, scales, origin, and types are widely developed in loess slopes, which can significantly control the structure, hydro-mechanical properties, damage regulations and deformation failure pattern of the slope. A series of major engineering projects have been implemented on the Loess Plateau of China. These projects have formed many loess slopes, which are prone to failure induced by loading. However, the failure mechanism of heap-loading loess slope, especially the influence of structural plane on slope failure, is not clear. Therefore, based on the investigation and analysis of the characteristics of loess structural planes, a large-scale model experiment was carried out, and the deformation process and failure mechanism of loess landslide induced by loading were systematically investigated. The soil pressure distribution, plastic state, and deformation characteristics of the slope were analyzed to reveal the influence of the structural plane on slope failure. The results show that the existence of the structural plane changed the stress field of the loess slope, forming a preferential yielding region around the structural plane, making the structural plane more likely to become a potential sliding surface. Different increases of earth pressure in the x- and z-direction is the main reason for the change in the extension angle of the structural plane. The propagation of the shear zone presents a typical “double slip surface” structure. The failure process of the loess slope induced by loading could be generalized into structural plane extension, shear band initiation, shear band penetration, and sliding failure stages.

Growing recognition of human impacts on streamflow regimes has driven efforts to integrate water‐management modules into hydrological models to improve simulation accuracy. Yet data constraints often force simplifying assumptions, which may introduce unintended biases and obscure true human influences. To address this, we compile a data inventory of human interventions in hydrological systems Data_IH2$\\left(Data\\text{\\_}I{H}^{2}\\right)$for the Contiguous United States. Data_IH2$Data\\text{\\_}I{H}^{2}$ , which encompasses reservoir operations, inter‐basin transfers, and water supplies for irrigation, municipal use, industry, and thermoelectric cooling, aims to replace oversimplifications with realistic, computationally efficient representations in large‐scale hydrological models. Next, we develop a modeling framework that leverages Data_IH2$Data\\text{\\_}I{H}^{2}$and the Budyko hypothesis to diagnose which management activities most strongly modify streamflow regimes and where those impacts occur. Applied to the Mississippi River Basin, our framework reveals that reservoir operation and irrigation together substantially alter flows in the Missouri and Arkansas‐White‐Red regions. Furthermore, the analysis identifies critical data and modeling gaps that must be addressed to obtain accurate streamflow simulation in different hydrologic regions, such as missing canal‐diversion records on the Platte River (Missouri region), insufficient tile‐drain representations in the Ohio region, and surface‐groundwater interactions in the Arkansas‐White‐Red region.

We introduce a numerical algorithm for solving dynamic economic models that merges stochastic simulation and projection approaches: we use simulation to approximate the ergodic measure of the solution, we cover the support of the constructed ergodic measure with a fixed grid, and we use projection techniques to accurately solve the model on that grid. The construction of the grid is the key novel piece of our analysis: we replace a large cloud of simulated points with a small set of “representative” points. We present three alternative techniques for constructing representative points: a clustering method, an ε-distinguishable set method, and a locally-adaptive variant of the ε-distinguishable set method. As an illustration, we solve one- and multi-agent neoclassical growth models and a large-scale new Keynesian model with a zero lower bound on nominal interest rates. The proposed solution algorithm is tractable in problems with high dimensionality (hundreds of state variables) on a desktop computer.