Related papers: MapLibre Tile: A Next Generation Vector Tile Forma…

Modern recommendation systems rely on real-valued embeddings of categorical features. Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size. We introduce a multi-layer embedding…

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

High-dimensional tensor models are notoriously computationally expensive to train. We present a meta-learning algorithm, MMT, that can significantly speed up the process for spatial tensor models. MMT leverages the property that spatial…

The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the…

Visualizing a complex network is computationally intensive process and depends heavily on the number of components in the network. One way to solve this problem is not to render the network in real time. PRE-render Content Using Tiles…

Model View Definition (MVD) is the standard methodology to define the data exchange requirements and rule constraints for Building Information Models (BIMs). In this paper, the MVDLite algorithm is proposed for the fast validation of MVD…

Massive multiple-input and multiple-output (MIMO) enables ultra-high throughput and low latency for tile-based adaptive virtual reality (VR) 360 video transmission in wireless network. In this paper, we consider a massive MIMO system where…

Mixture of Experts (MoE) models have achieved great success by significantly improving performance while maintaining computational efficiency through sparse expert activation. However, their enormous parameter sizes and memory demands pose…

Multimodal large language models (MLLMs) have made rapid progress in recent years, yet continue to struggle with low-level visual perception (LLVP) -- particularly the ability to accurately describe the geometric details of an image. This…

Transformer-based models have recently achieved outstanding performance in image matting. However, their application to high-resolution images remains challenging due to the quadratic complexity of global self-attention. To address this…

Creating visual layouts is a critical step in graphic design. Automatic generation of such layouts is essential for scalable and diverse visual designs. To advance conditional layout generation, we introduce BLT, a bidirectional layout…

Automated front-end engineering drastically reduces development cycles and minimizes manual coding overhead. While Generative AI has shown promise in translating designs to code, current solutions often produce monolithic scripts, failing…

Active research is currently underway to enhance the efficiency of vision transformers (ViTs). Most studies have focused solely on effective token mixers, overlooking the potential relationship with normalization. To boost diverse feature…

Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications. The state-of-the-art multi-vector paradigm excels in…

Dimensionality reduction (DR) plays a crucial role in various fields, including data engineering and visualization, by simplifying complex datasets while retaining essential information. However, achieving both high DR accuracy and strong…

Optical and optoelectronic approaches of performing matrix-vector multiplication (MVM) operations have shown the great promise of accelerating machine learning (ML) algorithms with unprecedented performance. The incorporation of…

Modern video retrieval systems are expected to handle diverse tasks ranging from corpus-level retrieval, fine-grained moment localization to flexible multimodal querying. Specialized architectures achieve strong retrieval performance by…

Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversion rates, and other optimization events. To support a wide variety of product surfaces and…

This paper presents a vector HD-mapping algorithm that formulates the mapping as a tracking task and uses a history of memory latents to ensure consistent reconstructions over time. Our method, MapTracker, accumulates a sensor stream into…

This paper investigates a cross-lingual document embedding method that improves the current Neural machine Translation framework based Document Vector (NTDV or simply NV). NV is developed with a self-attention mechanism under the neural…