Related papers: H3DFact: Heterogeneous 3D Integrated CIM for Facto…
In recent times, a plethora of hardware accelerators have been put forth for graph learning applications such as vertex classification and graph classification. However, previous works have paid little attention to Knowledge Graph…
While NeRF-based 3D-aware image generation methods enable viewpoint control, limitations still remain to be adopted to various 3D applications. Due to their view-dependent and light-entangled volume representation, the 3D geometry presents…
Hyperdimensional computing (HDC) is an increasingly popular computing paradigm with immense potential for future intelligent applications. Although the main ideas already took form in the 1990s, HDC recently gained significant attention,…
Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes, interactive elements, and functional relationship edges. However, their potential remains…
Modern imaging techniques at the molecular scale rely on utilizing novel coherent light sources like X-ray free electron lasers for the ultimate goal of visualizing such objects as individual biomolecules rather than crystals. Here, unlike…
We introduce the Holographic Knowledge Manifold (HKM), a four-phase pipeline that achieves zero catastrophic forgetting in AI knowledge representation while maintaining minimal memory growth and high efficiency. Leveraging fractal…
This paper develops a mathematical argument and algorithms for building representations of data from event-based cameras, that we call Fast Feature Field ($\text{F}^3$). We learn this representation by predicting future events from past…
Class-incremental learning (CIL) has achieved remarkable successes in learning new classes consecutively while overcoming catastrophic forgetting on old categories. However, most existing CIL methods unreasonably assume that all old…
Both high-level and high-resolution feature representations are of great importance in various visual understanding tasks. To acquire high-resolution feature maps with high-level semantic information, one common strategy is to adopt dilated…
Vision Transformers (ViTs) have established new performance benchmarks in vision tasks such as image recognition and object detection. However, these advancements come with significant demands for memory and computational resources,…
Recent progress in artificial intelligence has encouraged numerous attempts to understand and decode human visual system from brain signals. These prior works typically align neural activity independently with semantic and perceptual…
The capability of holography to project three-dimensional (3D) images and correct for aberrations offers much potential to enhance optical control in light-based 3D printing. Notably, multi-beam multi-wavelength holographic systems…
Federated Learning (FL) enables collaborative intelligence across decentralized data source devices in a privacy-preserving way. While substantial research attention has been drawn to optimizing the learning process for an individual task,…
Semantic image segmentation is one of the most challenged tasks in computer vision. In this paper, we propose a highly fused convolutional network, which consists of three parts: feature downsampling, combined feature upsampling and…
Recent advances in localized implicit functions have enabled neural implicit representation to be scalable to large scenes. However, the regular subdivision of 3D space employed by these approaches fails to take into account the sparsity of…
The reconstruction of visual information from brain activity fosters interdisciplinary integration between neuroscience and computer vision. However, existing methods still face challenges in accurately recovering highly complex visual…
The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass.…
We address the problem of 3D object detection, that is, estimating 3D object bounding boxes from point clouds. 3D object detection methods exploit either voxel-based or point-based features to represent 3D objects in a scene. Voxel-based…
Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency…
Three-dimensional (3D)-stacking technology, which enables the integration of DRAM and logic dies, offers high bandwidth and low energy consumption. This technology also empowers new memory designs for executing tasks not traditionally…