Dynamic reasoning frameworks such as Chain of Thought (CoT), Tree of Thought (ToT), and Graph of Thought (GoT) have greatly enhanced the logical reasoning capabilities of large language models (LLMs). However, their effectiveness depends on appropriately setting the granularity of each thought. Long thoughts may lead to higher error rates due to insufficient utilization of control signals, while short thoughts can reduce reasoning efficiency. This study introduces two dynamic step size control methods—Dynamic-step ToT and Chain-ToT—to address this issue. Dynamic-step ToT adjusts the number of reasoning steps in each thought dynamically to balance accuracy and efficiency, while Chain-ToT employs a linear reasoning approach, progressively expanding the step size until errors are detected. Experimental results on cutting-edge models such as Llama 3.1, Qwen 2.5, and GPT-4o-mini, as well as datasets including MATH, AIME, and MMLU-pro, demonstrate that our proposed dynamic step size methods significantly improve reasoning efficiency. This is achieved while maintaining or even surpassing the accuracy levels of standard ToT frameworks in complex reasoning tasks. We will release the code and results.

With growing cloud server usage and frequent privacy breaches, text privacy protection research has gained significant attention. However, applying differential privacy noise to individual tokens causes semantic loss in sentence-level tasks and remains vulnerable to reconstruction attacks. Previous studies show privacy attacks can infer sensitive information using inter-part-of-speech context, leading to leakage. To address poor semantic consistency and weak privacy protection in single-token strategies, we propose SCText—a hierarchical part-of-speech contextual semantics framework. This solution employs hierarchical positioning, context influence matrices, and exponential noise desensitization to preserve semantic consistency while preventing leakage. Experiments demonstrate significantly enhanced semantic preservation and privacy-attack resistance between original and desensitized texts.

Nonrigid deformation (NRD) and image noise in multimodal remote sensing images (MRSI) lead to abrupt changes in feature directions, resulting in sensitivity to rotational variation, sparse correct matches, and high false match rates. In order to address these challenges, this article proposes a second-order tensor orientation feature transformation (SOFT) method to improve the rotational invariance of MRSI matching and increase the number of correct matches (NCMs). The SOFT method has two main contributions: 1) a novel second-order tensor orientation descriptor is constructed by generating a tensor orientation feature map using a designed second-order tensor function, which is then combined with a gradient location and orientation histogram (GLOH)-like descriptor framework to achieve robust rotational invariance in multimodal image matching and 2) an error-removal global-local iterative optimization (EGIO) is introduced, employing a skewness of mixed pixel intensity (SMPI) function to automatically select matching seed points, followed by an iterative partition optimization strategy for refining corresponding points. Experiments on 744 groups of typical MRSIs demonstrate that the SOFT method significantly outperforms nine state-of-the-art methods, achieving an average 97% improvement in the NCMs, an average 25.51% improvement in the rate of correct matches (RCMs), and an average reduction in RMSE of 2.69 pixels. The proposed SOFT method, thus, offers robust MRSI matching with strong rotational invariance and precise identification of corresponding points, proving its effectiveness for complex remote sensing scenarios. Access to experiment-related data and codes will be provided athttps://skyearth.org/research/.

Semantic Scene Completion (SSC) aims to reconstruct complete 3D scenes with precise voxel-wise semantics from the single-view incomplete input data, a crucial but highly challenging problem for scene understanding. Although SSC has seen significant progress due to the introduction of 2D semantic priors in recent years, the occluded parts, especially the rear-view of the scenes, are still poorly completed and segmented. To ameliorate this issue, we propose a novel deep learning framework for 3D SSC, named Planar Convolution and Attention-based Network (PCANet), to effectively extend high-precision predictions of the front-view surface to the rear-view occluded areas. Specifically, we decompose the traditional convolutional layer into three successive planar convolutions to form a Planar Convolution Residual (PCR) block, which maintains the planar features of the 3D scene. Afterward, the Planar Attention Module (PAM) is proposed to capture three different planar attentions and harvest the global context from the front surface to the rear occluded areas to improve the overall accuracy. Extensive experiments on the real NYU and NYUCAD datasets and the synthetic SUNCG-RGBD dataset demonstrate that our proposed framework can generate high-quality SSC results in both front and rear views and outperforms the state-of-the-art approaches trained in an end-to-end manner without additional data.

The distribution of feature vectors plays a critical role in image registration. In this letter, we propose a novel approach for remote sensing image registration based on marginal distribution adaptation. First, we map the feature vectors of reference and sensed images into a latent space. Transfer component analysis (TCA) is employed to compute the transformation matrix by minimizing the maximum mean discrepancy (MMD). Then, we match feature vectors in the latent space where their marginal distributions are similar, which can increase correct correspondences and enhance registration accuracy. Finally, we test the proposed algorithm on ten real image pairs. The effectiveness and efficiency of our approach are verified by experimental results.

Traditional image feature matching methods cannot obtain satisfactory results for multi-modal remote sensing images (MRSIs) in most cases because different imaging mechanisms bring significant nonlinear radiation distortion differences (NRD) and complicated geometric distortion. The key to MRSI matching is trying to weakening or eliminating the NRD and extract more edge features. This paper introduces a new robust MRSI matching method based on co-occurrence filter (CoF) space matching (CoFSM). Our algorithm has three steps: (1) a new co-occurrence scale space based on CoF is constructed, and the feature points in the new scale space are extracted by the optimized image gradient; (2) the gradient location and orientation histogram algorithm is used to construct a 152-dimensional log-polar descriptor, which makes the multi-modal image description more robust; and (3) a position-optimized Euclidean distance function is established, which is used to calculate the displacement error of the feature points in the horizontal and vertical directions to optimize the matching distance function. The optimization results then are rematched, and the outliers are eliminated using a fast sample consensus algorithm. We performed comparison experiments on our CoFSM method with the scale-invariant feature transform (SIFT), upright-SIFT, PSO-SIFT, and radiation-variation insensitive feature transform (RIFT) methods using a multi-modal image dataset. The algorithms of each method were comprehensively evaluated both qualitatively and quantitatively. Our experimental results show that our proposed CoFSM method can obtain satisfactory results both in the number of corresponding points and the accuracy of its root mean square error. The average number of obtained matches is namely 489.52 of CoFSM, and 412.52 of RIFT. As mentioned earlier, the matching effect of the proposed method was significantly greater than the three state-of-art methods. Our proposed CoFSM method achieved good effectiveness and robustness. Executable programs of CoFSM and MRSI datasets are published: https://skyearth.org/publication/project/CoFSM/.

Multimodal image registration is critical yet challenging for remote sensing image processing. Due to the large nonlinear intensity differences between the multimodal images, conventional search algorithms tend to get trapped into local optima when optimizing the transformation parameters by maximizing mutual information (MI). To address this problem, inspired by transfer learning, we propose a novel search algorithm named transfer optimization (TO), which can be applied to any optimizer. In TO, an optimizer transfers its better individuals to the other optimizer in each iteration. Thus, TO can share information between two optimizers and take advantage of their search mechanisms, which is helpful to avoid the local optima. Then, the registration of the multimodal remote sensing images using TO is presented. We compare the proposed algorithm with several state-of-the-art algorithms on real and simulated image pairs. Experimental results demonstrate the superiority of our algorithm in terms of registration accuracy.

In the co-design process of hardware/software (HW/SW) system, especially for large and complicated embedded systems, HW/SW partitioning is a challenging step. Among different heuristic approaches, particle swarm optimization (PSO) has the advantages of simple implementation and computational efficiency, which is suitable for solving large-scale problems. This paper presents a conformity particle swarm optimization with fireworks explosion operation (CPSO-FEO) to solve large-scale HW/SW partitioning. First, the proposed CPSO algorithm simulates the conformist mentality from biology research. The CPSO particles with psychological conformist always try to move toward a secure point and avoid being attacked by natural enemy. In this way, there is a greater possibility to increase population diversity and avoid local optimum in CPSO. Next, to enhance the search accuracy and solution quality, an improved FEO with new initialization strategy is presented and is combined with CPSO algorithm to search a better position for the global best position. This combination can keep both the diversified and intensified searching. At last, the experiments on benchmarks and large-scale HW/SW partitioning demonstrate the efficiency of the proposed algorithm.