Binary Code Similarity Detection (BCSD) has extensive applications in various fields such as vulnerability detection and software component analysis. However, many existing approaches still suffer from several challenges, including low accuracy in capturing semantic information from binary code, excessive time cost in feature extraction process. To address these issues, we propose a modified Bert-based model named FGF-Bert with a fine-grained feature fusion strategy for BCSD. In FGF-Bert, we numerically describe the jump execution information in binary functions and design a fine-grained feature fusion strategy to extract and fuse function-level semantic feature and control flow feature of binary functions accurately and efficiently. Moreover, we design a practical function embedding similarity detection method to identify candidate vulnerable functions by which we implement vulnerability detection. Our experiment results demonstrate FGF-Bert has a good performance in representation of binary code and outperforms state-of-the-art (SOTA) BCSD approaches in terms of effectiveness, practicality and efficiency. The accuracies of four function representation masked language models (MLM) tasks are 97.5%, 96.4%, 97.7%, and 97.5%, respectively, and the accuracy of BCSD is 98.8%. For real-world vulnerability detection, FGF-Bert outperforms SOTA approach jTrans on the recall metric by 16.4% (from 68.0% to 84.4%) on average.

Spatially resolved transcriptomics data are being used in a revolutionary way to decipher the spatial pattern of gene expression and the spatial architecture of cell types. Much work has been done to exploit the genomic spatial architectures of cells. Such work is based on the common assumption that gene expression profiles of spatially adjacent spots are more similar than those of more distant spots. However, related work might not consider the nonlocal spatial co-expression dependency, which can better characterize the tissue architectures. Therefore, we propose MuCoST, a Multi-view graph Contrastive learning framework for deciphering complex Spatially resolved Transcriptomic architectures with dual scale structural dependency. To achieve this, we employ spot dependency augmentation by fusing gene expression correlation and spatial location proximity, thereby enabling MuCoST to model both nonlocal spatial co-expression dependency and spatially adjacent dependency. We benchmark MuCoST on four datasets, and we compare it with other state-of-the-art spatial domain identification methods. We demonstrate that MuCoST achieves the highest accuracy on spatial domain identification from various datasets. In particular, MuCoST accurately deciphers subtle biological textures and elaborates the variation of spatially functional patterns.

This article considers a general model of distributed convex optimization with possibly local constraints, coupled equality constraints, and coupled inequality constraints, where the coupled equality constraints are affine and the coupled inequality constraints can be nonaffine. To solve this problem, we present two algorithms. The first algorithm is similar to a dual subgradient algorithm that requires a center node in the network. The main advantage of the first algorithm is that it achieves the optimal convergence rate O([1/√k]) . Moreover, it does not require additional treatment for the primal recovery. These merits are achieved by using an iterate-averaging feedback technique on the basis of the dual subgradient method. The second algorithm further removes the requirement of a center node by employing consensus tracking iterates. As a result, the second algorithm is fully distributed at the price of achieving an O([lnk/√k]) convergence rate.

In this paper, we study the distributed Nash equilibrium (NE) seeking problem for a class of aggregative games with players described by uncertain perturbed nonlinear dynamics. To seek the NE, each player needs to construct a distributed algorithm based on information of its cost function and the exchanging information obtained from its neighbors. By combining the internal model principle and the average consensus technique, we propose a distributed gradient-based algorithm for the players. This paper not only assures the NE seeking of aggregative games but also achieves the disturbance rejection of external disturbances.

Considering a game with quadratic cost functions, this paper presents a distributed algorithm with security, whereby each player updates its strategy variable without using its private data and still achieves the Nash equilibrium. By using the theory of differential inclusions, Lyapunov function and invariance principle, the algorithm is proved to be convergent. Our algorithm can be used when it is required to seek the Nash equilibrium without disclosure of private data.

In this paper, a distributed resource allocation problem with nonsmooth local cost functions is considered, where the interaction among agents is depicted by strongly connected and weight-balanced digraphs. Here the decision variable of each agent is within a local feasibility constraint described as a convex set, and all the decision variables have to satisfy a network resource constraint, which is the sum of available resources. To solve the problem, a distributed continuous-time algorithm is developed by virtue of differentiated projection operations and differential inclusions, and its convergence to the optimal solution is proved via the set-valued LaSalle invariance principle. Furthermore, the exponential convergence of the proposed algorithm can be achieved when the local cost functions are differentiable with Lipschitz gradients and there are no local feasibility constraints. Finally, numerical examples are given to verify the effectiveness of the proposed algorithms.

Imagine taking a selfie video with your mobile phone and getting as output a 3D model of your head (face and 3D hair strands) that can be later used in VR, AR, and any other domain. State of the art hair reconstruction methods allow either a single photo (thus compromising 3D quality) or multiple views, but they require manual user interaction (manual hair segmentation and capture of fixed camera views that span full 360°). In this paper, we describe a system that can completely automatically create a reconstruction from any video (even a selfie video), and we don't require specific views, since taking your -90°, 90°, and full back views is not feasible in a selfie capture. In the core of our system, in addition to the automatization components, hair strands are estimated and deformed in 3D (rather than 2D as in state of the art) thus enabling superior results. We provide qualitative, quantitative, and Mechanical Turk human studies that support the proposed system, and show results on a diverse variety of videos (8 different celebrity videos, 9 selfie mobile videos, spanning age, gender, hair length, type, and styling).

We present an algorithm that takes a single frame of a person's face from a depth camera, e.g., Kinect, and produces a high-resolution 3D mesh of the input face. We leverage a dataset of 3D face meshes of 1204 distinct individuals ranging from age 3 to 40, captured in a neutral expression. We divide the input depth frame into semantically significant regions (eyes, nose, mouth, cheeks) and search the database for the best matching shape per region. We further combine the input depth frame with the matched database shapes into a single mesh that results in a highresolution shape of the input person. Our system is fully automatic and uses only depth data for matching, making it invariant to imaging conditions. We evaluate our results using ground truth shapes, as well as compare to state-of-the-art shape estimation methods. We demonstrate the robustness of our local matching approach with high-quality reconstruction of faces that fall outside of the dataset span, e.g., faces older than 40 years old, facial expressions, and different ethnicities.