Related papers: SimLOD: Simultaneous LOD Generation and Rendering

Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Existing acceleration techniques either require extensive model…

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

Deep neural networks have revolutionized 3D point cloud processing, yet efficiently handling large and irregular point clouds remains challenging. To tackle this problem, we introduce FastPoint, a novel software-based acceleration technique…

Diffusion-based Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive models, offering unique advantages through bidirectional attention and parallel generation paradigms. However, the generation results…

RAPID-LLM is a unified performance modeling framework for large language model (LLM) training and inference on GPU clusters. It couples a DeepFlow-based frontend that generates hardware-aware, operator-level Chakra execution traces from an…

Graphic design visually conveys information and data by creating and combining text, images and graphics. Two-stage methods that rely primarily on layout generation lack creativity and intelligence, making graphic design still…

Fine-tuning Vision-Language Models (VLMs) is a common strategy to improve performance following an ad-hoc data collection and annotation of real-world scenes. However, this process is often prone to biases, errors, and distribution…

Depth estimation is an important step in many computer vision problems such as 3D reconstruction, novel view synthesis, and computational photography. Most existing work focuses on depth estimation from single frames. When applied to…

We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typically associated with diffusion-based methods. By shifting…

We present a novel 3D mapping method leveraging the recent progress in neural implicit representation for 3D reconstruction. Most existing state-of-the-art neural implicit representation methods are limited to object-level reconstructions…

3D Gaussian Splatting (3DGS) has become a state-of-the-art framework for real-time, high-fidelity novel view synthesis. However, its substantial storage requirements and inherently unstructured representation pose challenges for deployment…

Lidar point cloud synthesis based on generative models offers a promising solution to augment deep learning pipelines, particularly when real-world data is scarce or lacks diversity. By enabling flexible object manipulation, this synthesis…

Speculative decoding has emerged as a promising technique for large language model (LLM) inference by accelerating autoregressive decoding via draft-then-verify. This paper studies a new edge scenario with multi-user inference, where draft…

While deep learning-based methods have demonstrated outstanding results in numerous domains, some important functionalities are missing. Resolution scalability is one of them. In this work, we introduce a novel architecture, dubbed…

Video generation models often operate under the assumption of fixed frame rates, which leads to suboptimal performance when it comes to handling flexible frame rates (e.g., increasing the frame rate of the more dynamic portion of the video…

Graph embeddings map graph nodes to continuous vectors and are foundational to community detection, recommendation, and many scientific applications. At billion-scale, however, existing graph embedding systems face a trade-off: they either…

A streaming algorithm to compute the spectral proper orthogonal decomposition (SPOD) of stationary random processes is presented. As new data becomes available, an incremental update of the truncated eigenbasis of the estimated…

The rapid growth of deep learning has driven exponential increases in model parameters and computational demands. NVIDIA GPUs and their CUDA-based software ecosystem provide robust support for parallel computing, significantly alleviating…

Log-Structured-Merge (LSM) tree-based key value stores are facing critical challenges of fully leveraging the dramatic performance improvements of the underlying storage devices, which makes the compaction operations of LSM key value stores…

Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, prohibitive training costs, and bandwidth constraints. While…