Related papers: TurboReg: TurboClique for Robust and Efficient Poi…
Until recently, the most accurate methods for time series classification were limited by high computational complexity. ROCKET achieves state-of-the-art accuracy with a fraction of the computational expense of most existing methods by…
Deploying deep neural networks on mobile devices is increasingly important but remains challenging due to limited computing resources. On the other hand, their unified memory architecture and narrower gap between CPU and GPU performance…
Although deep learning-based personalized recommendation systems provide qualified recommendations, they strain data center resources. The main bottleneck is the embedding layer, which is highly memory-intensive due to its sparse, irregular…
Despite recent progress in video generation, inference speed remains a major bottleneck. A common acceleration strategy involves reusing model outputs via caching mechanisms at fixed intervals. However, we find that such fixed-frequency…
Cross-source point cloud registration, which aims to align point cloud data from different sensors, is a fundamental task in 3D vision. However, compared to the same-source point cloud registration, cross-source registration faces two core…
Point cloud registration is an important task in robotics and autonomous driving to estimate the ego-motion of the vehicle. Recent advances following the coarse-to-fine manner show promising potential in point cloud registration. However,…
Accurate multi-step port-of-call sequence prediction is vital for tactical resource orchestration and logistical efficiency. However, existing methods struggle with unreliable voyage schedules and the inability of AIS data to provide…
Surrogate modeling has emerged as a powerful tool to accelerate Computational Fluid Dynamics (CFD) simulations. Existing 3D geometric learning models based on point clouds, voxels, meshes, or graphs depend on explicit geometric…
We present CLIPPER (Consistent LInking, Pruning, and Pairwise Error Rectification), a framework for robust data association in the presence of noise and outliers. We formulate the problem in a graph-theoretic framework using the notion of…
Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping region sampling…
In this paper, we propose a novel method to compute triangle counting on GPUs. Unlike previous formulations of graph matching, our approach is BFS-based by traversing the graph in an all-source-BFS manner and thus can be mapped onto GPUs in…
Point cloud registration for 3D objects is a challenging task due to sparse and noisy measurements, incomplete observations and large transformations. In this work, we propose \textbf{G}raph \textbf{M}atching \textbf{C}onsensus…
Evaluating high-dimensional integrals via deep hierarchical recurrences is a dominant cost in quantum chemistry. While CPUs manage these efficiently, GPUs suffer a critical mismatch: limited per-thread memory is quickly overwhelmed by an…
Non-rigid point cloud registration is a critical challenge in 3D scene understanding, particularly in surgical navigation. Although existing methods achieve excellent performance when trained on large-scale, high-quality datasets, these…
We study efficient algorithms for recovering cliques in dense random intersection graphs (RIGs). In this model, $d = n^{\Omega(1)}$ cliques of size approximately $k$ are randomly planted by choosing the vertices to participate in each…
Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases. However, retrievals from large databases can constitute a substantial portion of the overall…
Clique partitioning is a fundamental network clustering task, with applications in a wide range of computational sciences. It involves identifying an optimal partition of the nodes for a real-valued weighted graph according to the edge…
Shifted-and-Duplicated-Kernel (SDK) mapping has emerged as an effective strategy to accelerate convolutional layers on compute-in-memory (CIM) hardware. However, existing SDK variants (e.g., VWC-SDK) merely optimize mapping for a single CIM…
In this paper, we present a new method for the multiview registration of point cloud. Previous multiview registration methods rely on exhaustive pairwise registration to construct a densely-connected pose graph and apply Iteratively…
We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences. The advantage of the feature-metric projection…