Constraint programming (CP) is a crucial technology for solving real-world constraint optimization problems (COPs), with the advantages of rich modeling semantics and high solving efficiency.Using large language models (LLMs) to generate formal modeling automatically for COPs is becoming a promising approach, which aims to build trustworthy neuro-symbolic AI with the help of symbolic solvers.However, CP has received less attention compared to works based on operations research (OR) models.We introduce ConstraintLLM, the first LLM specifically designed for CP modeling, which is trained on an open-source LLM with multiinstruction supervised fine-tuning.We propose the Constraint-Aware Retrieval Module (CARM) to increase the in-context learning capabilities, which is integrated in a Tree-of-Thoughts (ToT) framework with guided selfcorrection mechanism.Moreover, we construct and release IndusCP, the first industriallevel benchmark for CP modeling, which contains 140 challenging tasks from various domains.Our experiments demonstrate that ConstraintLLM achieves state-of-the-art solving accuracy across multiple benchmarks and outperforms the baselines by 2x on the new IndusCP benchmark.

Embodied intelligence requires precise reconstruction and rendering to simulate large-scale real-world data. Although 3D Gaussian Splatting (3DGS) has recently demonstrated high-quality results with real-time performance, it still faces challenges in indoor scenes with large, textureless regions, resulting in incomplete and noisy reconstructions due to poor point cloud initialization and underconstrained optimization. Inspired by the continuity of signed distance field (SDF), which naturally has advantages in modeling surfaces, we propose a unified optimization framework that integrates neural signed distance fields (SDFs) with 3DGS for accurate geometry reconstruction and real-time rendering. This framework incorporates a neural SDF field to guide the densification and pruning of Gaussians, enabling Gaussians to model scenes accurately even with poor initialized point clouds. Simultaneously, the geometry represented by Gaussians improves the efficiency of the SDF field by piloting its point sampling. Additionally, we introduce two regularization terms based on normal and edge priors to resolve geometric ambiguities in textureless areas and enhance detail accuracy. Extensive experiments in ScanNet and ScanNet++ show that our method achieves state-of-the-art performance in both surface reconstruction and novel view synthesis. Project page: https://xhd0612.github.io/GaussianRoom.github.io/

Remote sensing image restoration under cloud and haze occlusions poses a significant challenge due to severe spectral degradation and spatial distortions. While recent generative models have shown promise in image restoration, they struggle with three key issues: (1) Lack of precise annotations, making supervised methods unreliable; (2) Unintended interference with clear regions, leading to distortion in unaffected areas; (3) Spectral and structural inconsistencies in heavily occluded regions, limiting realistic recovery. To address these challenges, we propose Saliency-Guided Adaptive Random Diffusion Strategy(SG-ARD), a novel blind restoration framework that integrates saliency-aware guidance with adaptive diffusion for enhanced reconstruction. First, we introduce a Saliency-Guided Pseudo-label Generation module (SGPG) to identify degraded regions and generate pseudo-labels for blind restoration. Second, we propose an Adaptive Random Diffusion Correction Strategy (ARDC), which employs a Random-Walk-based Diffusion and an Adaptive Enhancement module to refine local and global texture pseudo-labels. Lastly, we design a Spectral-Aware Consistency Loss (SAC) to improve spectral fidelity, ensuring that the generated content aligns with the real spectral distribution. Extensive experiments on three large-scale remote sensing datasets demonstrate that SG-ARD outperforms state-of-the-art generative restoration models, producing high-fidelity, visually coherent remote sensing images.

Evolutionary algorithms (EAs) have significantly contributed to addressing large-scale crude oil scheduling problems (COSPs) that exceed the capabilities of mathematical programming. However, current research using EAs to resolve COSPs is limited to discrete-time models that assume uniform operation durations. While this simplification transforms COSPs into fixed-length optimization problems suitable for conventional EAs, it fails to adequately tackle the challenge posed by variable operation durations in COSPs. This limitation results in a compromised solution quality for EAs. To bridge the gap between large-scale COSPs and real-world refineries, this paper introduces the formulation of a continuous-time model for a large-scale COSP, accounting for varying operating durations and practical requirements. In an effort to enhance the effectiveness of EAs in optimizing COSPs represented in continuous time, we propose a variable-length constrained evolutionary algorithm (VLCEA). The variable-length encoding in VLCEA, tailored to the specific problem, facilitates the generation of high-quality solutions with variable lengths. This feature addresses the challenge of determining solution length in advance based on a priori knowledge using conventional methods. Additionally, VLCEA incorporates a sorting strategy and a niching-based selection to expedite the search for promising regions, aiming to achieve better solutions in less time. Experimental results on practical cases not only verify that the continuous-time model produces higher quality solutions compared to the discrete-time model but also demonstrate that VLCEA significantly outperforms five state-of-the-art large-scale EAs with fixed length when applied to the continuous-time model.Note to Practitioners—Crude oil scheduling is one of the most challenging problems in the refinery scheduling process. With the increasing size of scheduling tasks, traditional methods have become inefficient and inaccurate. To address this, evolutionary algorithms (EAs) have emerged as powerful tools for solving large-scale crude oil scheduling problems (COSPs). However, existing EA-based approaches often rely on a fixed number of decisions, resulting in suboptimal solutions when confronted with insufficient prior knowledge. To overcome these obstacles, we have developed a comprehensive continuous-time model specifically designed to address COSPs in real-world refineries. Additionally, we propose a variable-length constrained evolutionary algorithm (VLCEA) as an effective approach for resolving these complex scheduling problems. Computational results demonstrate that the VLCEA achieves superior performance compared to three state-of-the-art EAs in practical large-scale cases. Consequently, the proposed VLCEA exhibits significant potential for solving real-world refinery scheduling problems and can be extended to tackle other scheduling problems with an unfixed number of decisions.

Recently, neural implicit 3D reconstruction in indoor scenarios has become popular due to its simplicity and impressive performance. Previous works could produce complete results leveraging monocular priors of normal or depth. However, they may suffer from over-smoothed reconstructions and long-time optimization due to unbiased sampling and inaccurate monocular priors. In this paper, we propose a novel neural implicit surface reconstruction method, named FD-NeuS, to learn fine-detailed 3D models using multi-level importance sampling strategy and multi-view consistency methodology. Specifically, we leverage segmentation priors to guide region-based ray sampling, and use piecewise exponential functions as weights to pilot 3 D points sampling along the rays, ensuring more attention on important regions. In addition, we introduce multi-view feature consistency and multi-view normal consistency as supervision and uncertainty respectively, which further improve the reconstruction of details. Extensive quantitative and qualitative results show that FD-NeuS outperforms existing methods in various scenes.

The choice of activation function in deep learning is crucial to the performance of neural networks. The activation function used in conventional deep learning remains unchanged for neural networks of different depths, leading to performance degradation as the depth of the model increases. In this paper, we propose a $\operatorname{sigmoid}_{n}$ dynamic activation function that can change with the depth of the neural network. We firstly introduced the dual relationship between the activation function and the probability generating function(PGF) from the perspective of the branching process, and explained the reason why the model performance of different activation functions decreases as the neural network deepens. Then, we use the law of large numbers in the super critical branching process to optimize the PGF and propose the sigmoid ${ }_{n}$ dynamic activation function through the dual relationship between the PGF and the activation function. Finally, to better extract the spatial context information of the image, we add a convolution channel based on the sigmoid ${ }_{n}$ dynamic activation function and propose a two-dimensional Fsigmoid ${ }_{n}$ dynamic activation function. Experiments on CIFAR-10 and CIFAR-100 datasets verify the superiority of the proposed sigmoid ${ }_{n}$ activation function.

Most existing robotic datasets capture static scene data and thus are limited in evaluating robots’ dynamic performance. To address this, we present a mobile robot oriented large-scale indoor dataset, denoted as THUD (Tsinghua University Dynamic) robotic dataset, for training and evaluating their dynamic scene understanding algorithms. Specifically, the THUD dataset construction is first detailed, including organization, acquisition, and annotation methods. It comprises both real-world and synthetic data, collected with a real robot platform and a physical simulation platform, respectively. Our current dataset includes 13 larges-scale dynamic scenarios, 90K image frames, 20M 2D/3D bounding boxes of static and dynamic objects, camera poses, and IMU. The dataset is still continuously expanding. Then, the performance of mainstream indoor scene understanding tasks, e.g. 3D object detection, semantic segmentation, and robot relocalization, is evaluated on our THUD dataset. These experiments reveal serious challenges for some robot scene understanding tasks in dynamic scenes. By sharing this dataset, we aim to foster and iterate new mobile robot algorithms quickly for robot actual working dynamic environment, i.e. complex crowded dynamic scenes.

SUMMARY: With the continuous development of high-throughput sequencing technology, bioinformatic analysis of omics data plays an increasingly important role in life science research. Many R packages are widely used for omics analysis, such as DESeq2, clusterProfiler and STRINGdb. And some online tools based on them have been developed to free bench scientists from programming with these R packages. However, the charts generated by these tools are usually in a fixed, non-editable format and often fail to clearly demonstrate the details the researchers intend to express. To address these issues, we have created Visual Omics, an online tool for omics data analysis and scientific chart editing. Visual Omics integrates multiple omics analyses which include differential expression analysis, enrichment analysis, protein domain prediction and protein-protein interaction analysis with extensive graph presentations. It can also independently plot and customize basic charts that are involved in omics analysis, such as various PCA/PCoA plots, bar plots, box plots, heat maps, set intersection diagrams, bubble charts and volcano plots. A distinguishing feature of Visual Omics is that it allows users to perform one-stop omics data analyses without programming, iteratively explore the form and layout of graphs online and fine-tune parameters to generate charts that meet publication requirements. AVAILABILITY AND IMPLEMENTATION: Visual Omics can be used at http://bioinfo.ihb.ac.cn/visomics. Source code can be downloaded at http://bioinfo.ihb.ac.cn/software/visomics/visomics-1.1.tar.gz. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

In large refineries, the resource-oriented plan of crude oil is commonly required to be tractable and decomposable for practical operation scheduling, especially for large-scale scheduling. To this end, a framework of hybrid optimization based on plan decomposition (FHO/PD) is proposed, which mainly depends on evolutionary algorithms to realize the flexible decomposition from large-scale planning to scheduling and takes advantage of mathematical programming to improve the solving efficiency synchronously. Finally, the experimental results on a practical case suggest that the proposed method has shown great flexibility and applicability in crude oil scheduling.