Correspondence-based point cloud registration (PCR) plays a key role in robotics and computer vision. However, challenges like sensor noises, object occlusions, and descriptor limitations inevitably result in numerous outliers. RANSAC family is the most popular outlier removal solution. However, the requisite iterations escalate exponentially with the outlier ratio, rendering it far inferior to existing methods (SC2PCR [1], MAC [2] etc.) in terms of accuracy or speed. Thus, we propose a two-stage consensus filtering (TCF) that elevates RANSAC to state-of-the-art (SOTA) speed and accuracy. Firstly, one-point RANSAC obtains a consensus set based on length consistency. Subsequently, two-point RANSAC refines the set via angle consistency. Then, three-point RANSAC computes a coarse pose and removes outliers based on transformed correspondence's distances. Drawing on optimizations from one-point and two-point RANSAC, three-point RANSAC requires only a few iterations. Eventually, an iterative reweighted least squares (IRLS) is applied to yield the optimal pose. Experiments on the large-scale KITTI and ETH datasets demonstrate our method achieves up to three-orders-of-magnitude speedup compared to MAC while maintaining registration accuracy and recall. Our code is available at https://github.com/ShiPC-AI/TCF .

Large language models (LLMs) often struggle with knowledge-intensive tasks due to a lack of background knowledge and a tendency to hallucinate. To address these limitations, integrating knowledge graphs (KGs) with LLMs has been intensively studied. Existing KG-enhanced LLMs focus on supplementary factual knowledge, but still struggle with solving complex questions. We argue that refining the relationships among facts and organizing them into a logically consistent reasoning path is equally important as factual knowledge itself. Despite their potential, extracting reliable reasoning paths from KGs poses the following challenges: the complexity of graph structures and the existence of multiple generated paths, making it difficult to distinguish between useful and redundant ones. To tackle these challenges, we propose the RRP framework to mine the knowledge graph, which combines the semantic strengths of LLMs with structural information obtained through relation embedding and bidirectional distribution learning. Additionally, we introduce a rethinking module that evaluates and refines reasoning paths according to their significance. Experimental results on two public datasets show that RRP achieves state-of-the-art performance compared to existing baseline methods. Moreover, RRP can be easily integrated into various LLMs to enhance their reasoning abilities in a plug-and-play manner. By generating high-quality reasoning paths tailored to specific questions, RRP distills effective guidance for LLM reasoning.

Lidar-based Place Recognition (LPR) is crucial for intelligent vehicle navigation. Existing methods generally create LiDAR descriptors for pairwise comparisons or employ prior maps for metric localization but face challenges in computational complexity, limited robustness, and excessive memory overhead. Thus, this paper offers a fresh perspective called Map Clustering Similarity (MCS), improving robustness while reducing memory and remarkably boosting efficiency. We start by treating the ground as potential vehicle locations, i.e., virtual points, and introduce a compact LiDAR descriptor called Occupancy Scan Context (OcSC) to capture environmental occupancy from a bird's-eye view. We then employ the point cloud map, virtual points, and k-means clustering to condense the map data into 4Kb cluster centers. Eventually, we devise a two-phase online search algorithm. In the first phase, we extract the OcSC's ring key from online single-frame data, gauge its resemblance to map cluster centers to derive a cluster descriptor, and search loop candidates using the Spearman loss. In the second phase, we propose an occupancy loss to compare all candidates' OcSC descriptors to find the optimal candidate. Our method introduces a novel framework and merges advantages from existing solutions. Experiments on the KITTI dataset and two self-collected indoor sequences showcase MCS-BF's superior performance over mainstream methods in place recognition recall, F₁ score, and memory consumption. Additionally, MCS successfully balances runtime with accuracy. The source code will be available in https://github.com/ShiPC-AI/MCS.

Graph-based fraud detection (GFD) has garnered increasing attention due to its effectiveness in identifying fraudsters within multimedia data such as online transactions, product reviews, or telephone voices. However, the prevalent in-distribution (ID) assumption significantly impedes the generalization of GFD approaches to out-of-distribution (OOD) scenarios, which is a pervasive challenge considering the dynamic nature of fraudulent activities. In this paper, we introduce the Heterophilic Graph Invariant Learning Framework (HGIF), a novel approach to bolster the OOD generalization of GFD. HGIF addresses two pivotal challenges: creating diverse virtual training environments and adapting to varying target distributions. Leveraging edge-aware augmentation, HGIF efficiently generates multiple virtual training environments characterized by generalized heterophily distributions, thereby facilitating robust generalization against fraud graphs with diverse heterophily degrees. Moreover, HGIF employs a shared dual-channel encoder with heterophilic graph contrastive learning, enabling the model to acquire stable high-pass and low-pass node representations during training. During the Test-time Training phase, the shared dual-channel encoder is flexibly fine-tuned to adapt to the test distribution through graph contrastive learning. Extensive experiments showcase HGIF's superior performance over existing methods in OOD generalization, setting a new benchmark for GFD in OOD scenarios.

LiDAR panoptic segmentation (LPS) performs semantic and instance segmentation for things (foreground objects) and stuff (background elements), essential for scene perception and remote sensing. While most existing methods separate these tasks using distinct branches (i.e., semantic and instance), recent approaches have unified LPS through a query-based paradigm. However, the distinct spatial distributions of foreground objects and background elements in large-scale outdoor scenes pose challenges. This article presents DQFormer, a novel framework for unified LPS that employs a decoupled query workflow to adapt to the characteristics of things and stuff in outdoor scenes. It first utilizes a feature encoder to extract multiscale voxel-wise, point-wise, and bird’s eye view (BEV) features. Then, a decoupled query generator proposes informative queries by localizing things/stuff positions and fusing multilevel BEV embeddings. A query-oriented mask decoder uses masked cross-attention to decode segmentation masks, which are combined with query semantics to produce panoptic results. Extensive experiments on large-scale outdoor scenes, including the vehicular datasets nuScenes and SemanticKITTI, as well as the aerial point cloud dataset DALES, show that DQFormer outperforms superior methods by +1.8%, +0.9%, and +3.5% in panoptic quality (PQ), respectively. Code is available at https://github.com/yuyang-cloud/DQFormer

Network alignment is the matching of two networks with corresponding nodes that belong to the same user or entity. The most common application is to analyze which accounts belong to the same user in two social networks. Most of existing techniques rely on matrix factorization so that they cannot be scaled to large-scale networks, are constrained by strict constraints, and cannot learn node embedding without a training set. In this paper, we propose an unsupervised network alignment model based on multi-level graph attention networks. The model uses multi-level graph attention network to learn the embedded representation of nodes, satisfying attribute and structure constraints of alignment. Augmented learning process is proposed to simulate attribute noise and structural noise to improve adaptability of the model. Extensive experiments on real datasets show that the proposed model performs better than the state-of-the-art network alignment model. We also demonstrate the robustness of the proposed model.