Related papers: LLM-Powered Code Analysis and Optimization for Gau…

As multimodal language models advance, their application to 3D scene understanding is a fast-growing frontier, driving the development of 3D Vision-Language Models (VLMs). Current methods show strong dependence on object detectors,…

Novel view synthesis (NVS) in low-light scenes remains a significant challenge due to degraded inputs characterized by severe noise, low dynamic range (LDR) and unreliable initialization. While recent NeRF-based approaches have shown…

Traditional 3D content representations include dense point clouds that consume large amounts of data and hence network bandwidth, while newer representations such as neural radiance fields suffer from poor frame rates due to their…

3D Gaussian Splatting (3DGS) has emerged as a cutting-edge technique for real-time radiance field rendering, offering state-of-the-art performance in terms of both quality and speed. 3DGS models a scene as a collection of three-dimensional…

Improving GPU kernel efficiency is crucial for advancing AI systems. Recent work has explored leveraging large language models (LLMs) for GPU kernel generation and optimization. However, existing LLM-based kernel optimization pipelines…

3D Gaussian Splatting has demonstrated notable success in large-scale scene reconstruction, but challenges persist due to high training memory consumption and storage overhead. Hybrid representations that integrate implicit and explicit…

Automatic software system optimization can improve software speed, reduce operating costs, and save energy. Traditional approaches to optimization rely on manual tuning and compiler heuristics, limiting their ability to generalize across…

Performance profiles of GPU kernels generated by tools such as Nsight Compute are rich in detail but are often challenging to interpret. To achieve the best performance possible on a given GPU architecture, kernel developers need to spend…

We present a multi-GPU extension of the 3D Gaussian Splatting (3D-GS) pipeline for scientific visualization. Building on previous work that demonstrated high-fidelity isosurface reconstruction using Gaussian primitives, we incorporate a…

Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer…

Most 3D Gaussian Splatting (3D-GS) based methods for urban scenes initialize 3D Gaussians directly with 3D LiDAR points, which not only underutilizes LiDAR data capabilities but also overlooks the potential advantages of fusing LiDAR with…

Large Language Models (LLMs) have emerged as powerful tools for natural language processing tasks, revolutionizing the field with their ability to understand and generate human-like text. As the demand for more sophisticated LLMs continues…

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…

In the field of 3D dynamic scene reconstruction, how to balance model convergence rate and rendering quality has long been a critical challenge that urgently needs to be addressed, particularly in high-precision modeling of scenes with…

Recent advancements in 3D reconstruction coupled with neural rendering techniques have greatly improved the creation of photo-realistic 3D scenes, influencing both academic research and industry applications. The technique of 3D Gaussian…

While 3D Gaussian Splatting (3DGS) has revolutionized real-time photorealistic view synthesis, its fundamental reliance on symmetric Gaussian distributions introduces visual artifacts that hinder accurate spatial data exploration.…

Strong gravitational lensing is a powerful probe of cosmology and the dark matter distribution. Efficient lensing software is already a necessity to fully use its potential and the performance demands will only increase with the upcoming…

Dynamic 3D Gaussian splatting (3DGS) extends static 3DGS to render dynamic scenes, enabling AR/VR applications with moving objects. However, implementing dynamic 3DGS on edge devices faces challenges: (1) Loading all Gaussian parameters…

Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently. While prior work has…

The code written by developers usually suffers from efficiency problems and contain various performance bugs. These inefficiencies necessitate the research of automated refactoring methods for code optimization. Early research in code…