• 课程
  • AI未来·星火计划
  • 积分榜
  • 活动
    • AI创作狂欢价!摩尔学院携手BizyAir重磅补贴
    • 校园招聘 | 走近摩尔线程
    • AI 领航杯 -- 高性能云计算赛道 CV 模型训推挑战赛
    • 往期活动
  • 开发者
    • 社区
    • 博客
    • 论坛
    • 文档
    • 开源项目
  • 学术
    • 论文
  • 摩尔线程官网
  • 课程
  • AI未来·星火计划
  • 积分榜
  • 活动
    • AI创作狂欢价!摩尔学院携手BizyAir重磅补贴
    • 校园招聘 | 走近摩尔线程
    • AI 领航杯 -- 高性能云计算赛道 CV 模型训推挑战赛
    • 往期活动
  • 开发者
    • 社区
    • 博客
    • 论坛
    • 文档
    • 开源项目
  • 学术
    • 论文
  • 摩尔线程官网
    • 登录
    • 注册
  • 登录
  • 注册
  • 资讯频道
  • 活动
  • 论文
  • 新闻
11
10月

论文

RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians

RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians
In this work, we explore the possibility of training high-parameter 3D Gaussian splatting (3DGS) models on large-scale, high-resolution datasets. We d...
11
10月

论文

LiteGS: A High-performance Framework to Train 3DGS in Subminutes via System and Algorithm Codesign

LiteGS: A High-performance Framework to Train 3DGS in Subminutes via System and Algorithm Codesign
3DGaussian Splatting (3DGS) has emerged as promising alternative in 3D representation. However, it still suffers from high training cost. This paper i...
11
10月

论文

StableGS: A Floater-Free Framework for 3D Gaussian Splatting

StableGS: A Floater-Free Framework for 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) reconstructions are plagued by stubborn“floater”artifacts that degrade their geometric and visual fidelity. We are the fi...
11
10月

论文

DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents

DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents
The limitation of graphical user interface (GUI) data has been a significant barrier to the development of GUI agents today, especially for the deskto...
11
10月

论文

SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models

SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models
We introduce SEKI, a novel large language model (LLM)-based neural architecture search (NAS) method. Inspired by the chain-of-thought (CoT) paradigm i...
11
10月

论文

URPO: A Unified Reward and Policy Optimization Framework for Large Language Models

URPO: A Unified Reward and Policy Optimization Framework for Large Language Models
Large-scale alignment pipelines typically pair a policy model with a separately trained reward model whose parameters remain frozen during reinforceme...
11
10月

论文

Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference

Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference
The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conv...
11
10月

论文

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
Current Retrieval-Augmented Generation (RAG) systems concatenate and process numerous retrieved document chunks for prefill which requires a large vol...
11
10月

论文

A Full-duplex Speech Dialogue Scheme Based On Large Language Model

A Full-duplex Speech Dialogue Scheme Based On Large Language Model
We present a generative dialogue system capable of operating in a full-duplex manner, allowing for seamless interaction. It is based on a large langua...

热门焦点

1
RetinaGS: Scalable T...
2
MUSA 训练营 | 学 MUSA 赢大...
3
摩尔线程发布大模型训练仿真工具SimuM...
4
AI算力狂欢价!摩尔线程携手 AutoD...
5
盛夏算力狂欢,体验摩尔线程算力卡新征程
6
AI算力狂欢价!摩尔线程618算力补贴升...

热门标签

论文 开发者活动 校企联合课程 名企联合课程 名师大咖 第三方课程 摩尔线程 无证书 在线课程 在线实训 线下培训 有证书

热门评论

然然 评论于 StableGS: A Floater-Free Framework for 3D Gaussian Splatting
1111

编辑推荐

1
Round Attention: A N...
2
A Full-duplex Speech...

资源

  • 摩尔线程官网
  • 开发者社区
  • 技术文档
  • 技术博客
  • GitHub

产品

  • MTT S80
  • MTT S4000
  • MCCX D800
  • MTT KUAE
  • MUSA SDK

解决方案

  • 智算中心
  • 云桌面
  • DigitalME 数字人

活动

  • KUAE 试用
  • 开发者计划

政策

  • 用户服务协议
  • 合规声明
  • 法律声明
  • 隐私政策
  • 关于我们
Powered by 摩尔线程智能科技(北京)股份有限公司 课程存档
课程内容版权均归 摩尔线程智能科技(北京)股份有限公司 所有 京公网安备 11010802035174号
京ICP备2020041674号-2