Estimating the 6-DoF posture of parts in assembly-based modeling is a critical task in the fields of computer graphics, computer vision and robotics. A typical scenario involves enabling a machine agent to automatically assemble IKEA furniture using the provided parts. This paper presents HiFormer, a novel Hierarchical Transformer with Box-packed Positional Encoding, designed for highly automatic 3D part assembly. Our method addresses three important issues commonly encountered in 3D part assembly: 1) How to mitigate the overfitting problem associated with Transformer-based feature learning for 3D point clouds? 2) How to effectively model the relationships between the intragroup and intergroup parts? 3) How to compute positional encoding and integrate it into the Transformer for parts with diverse geometric forms in the coarse-to-fine assembly process? These challenges are tackled through three key contributions: 1) a multi-task 3D Swin Transformer with a two-stage training strategy for feature extraction, 2) a novel hierarchical Transformer for capturing part relationships at flattening, intragroup, and intergroup levels, and 3) an innovative box-packed positional encoding that enhances the Transformer by incorporating query, key, and value information derived from relative box positions. On the PartNet benchmark, our method outperforms the state-of-the-art PWH-MP model on three representative categories-Chair, Table, and Lamp-, achieving average improvements of 2.84% in Part Accuracy (PA) and 3.72% in Connection Accuracy (CA) for diversity modeling (with noise), and 3.55% in PA and 3.21% in CA for deterministic modeling (without noise).

Short-video recommender systems often exhibit a biased preference to recently released videos. However, not all videos become outdated; certain classic videos can still attract user’s attention. Such bias along temporal dimension can be further aggravated by the matching model between users and videos, because the model learns from preexisting interactions. From real data, we observe that different videos have varying sensitivities to recency in attracting users’ attention. Our analysis, based on a causal graph modeling short-video recommendation, suggests that the release interval serves as a confounder, establishing a backdoor path between users and videos. To address this confounding effect, we propose a model-agnostic causal architecture called Learning to Deconfound the Release Interval Bias (LDRI). LDRI enables jointly learning of the matching model and the video recency sensitivity perceptron. In the inference stage, we apply a backdoor adjustment, effectively blocking the backdoor path by intervening on each video. Extensive experiments on two benchmarks demonstrate that LDRI consistently outperforms backbone models and exhibits superior performance against state-of-the-art models. Additional comprehensive analyses confirm the deconfounding capability of LDRI.

OpenFlow has been applied to a variety of demands of the transmission quality of the Internet business and it is still growing on its way. To test this protocol with its evolution consideration, we analyzed the working process of OpenFlow protocol and constructed the CPN model through phasing firstly and then role division for version 1.0. In addition, the selection of tokens and their given values for CPN modeling are considered from the view of executable test sequenctionnce generation and further test case generation. During the process of modeling, we analyzed the OpenFlow evolution from version 1.0 to version 1.5, and the whole information we obtained were summed up to three evolution ways, (1) extending or contracting a value in one field, (2) extending or contracting one field in a packet and (3) adding a new packet. And an algorithm which converts test sequence to test case is presented and the total number of test cases is reported. The initialization phase is as an example to show our method feasibility.

OpenFlow is a new protocol which enables researchers to run experimental protocols in a network without changing the network topology. In the paper, we analyze and test OpenFlow based on a formal method, such as CPN (colored Petri net). To avoid state exploration, we mainly focus on testing the interaction property of OpenFlow. According to the latest OpenFlow specification, we construct its hierarchy CPN model and analyze the model with CPN tools. We propose two methods to generate the test sequences covering the interaction property. We also design an algorithm to generate the test sequences automatically. The related experiments are carefully designed and executed in four kinds of network environment, respectively.