自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+
  • 博客(37)
  • 收藏
  • 关注

原创 论文阅读笔记——RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete

RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete论文阅读笔记

2025-04-17 12:14:54 415

原创 论文阅读笔记——Generating Long Sequences with Sparse Transformers

Generating Long Sequences with Sparse Transformers 论文阅读笔记

2025-04-14 19:00:00 1154 1

原创 论文阅读笔记——Reactive Diffusion Policy

Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation 论文阅读笔记

2025-04-13 14:57:04 935 1

原创 论文阅读笔记——Multi-Token Attention

Multi-Token Attention 论文阅读笔记

2025-04-12 21:00:00 1307 1

原创 论文阅读笔记——GPT-1,GPT-2,GPT-3,InstructGPT

GPT-1,GPT-2,GPT-3,InstructGPT 论文阅读笔记

2025-04-09 12:00:00 1048 1

原创 论文阅读笔记——Deformable Radial Kernel Splatting

Deformable Radial Kernel Splatting 论文阅读笔记

2025-04-06 11:45:13 1135 1

原创 论文阅读笔记——RDT-1B: A DIFFUSION FOUNDATION MODEL FOR BIMANUAL MANIPULATION

RDT-1B: A DIFFUSION FOUNDATION MODEL FOR BIMANUAL MANIPULATION 论文阅读笔记

2025-04-05 16:54:44 1267 1

原创 论文阅读笔记——SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

SpatialVLA 论文阅读笔记

2025-04-01 12:36:27 1034 1

原创 论文阅读笔记——PointVLA: Injecting the 3D World into Vision-Language-Action Models

PointVLA 论文阅读笔记

2025-03-30 23:19:05 458 1

原创 论文阅读笔记——ReconDreamer

ReconDreamer 论文阅读笔记

2025-03-29 17:41:16 1361 1

原创 论文阅读笔记——ST-4DGS,WideRange4D

ST-4DGS,WideRange4D 论文阅读笔记

2025-03-27 20:42:20 1324 1

原创 论文阅读笔记——Diffuser,Diffusion Policy

Diffuser,Diffusion Policy 论文阅读笔记

2025-03-26 12:00:00 1125 1

原创 论文阅读笔记——Deformable 3DGS,4DGS

Deformable 3DGS,4DGS 论文阅读笔记

2025-03-25 12:00:00 2190 1

原创 论文阅读笔记——DriveDreamer4D, FreeVS

DriveDreamer4D, FreeVS 论文阅读笔记

2025-03-24 12:00:00 879 1

原创 论文阅读笔记——MTGS: Multi-Traversal Gaussian Splatting

MTGS: Multi-Traversal Gaussian Splatting 论文阅读笔记

2025-03-23 19:00:00 916 1

原创 论文阅读笔记——3D Gaussian Splatting for Real-Time Radiance Field Rendering

3D Gaussian Splatting for Real-Time Radiance Field Rendering 论文阅读笔记

2025-03-23 12:00:00 878 1

原创 论文阅读笔记——MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction

MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction 论文阅读笔记

2025-03-22 21:00:00 862 1

原创 论文阅读笔记——EWA Volume Splatting

EWA Volume Splatting 论文阅读笔记

2025-03-22 12:00:00 1103 1

原创 论文阅读笔记——MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes

MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes 论文阅读笔记

2025-03-20 12:00:00 881 1

原创 论文阅读笔记——MAGICDRIVE: STREET VIEW GENERATION WITH DIVERSE 3D GEOMETRY CONTROL

MAGICDRIVE: STREET VIEW GENERATION WITH DIVERSE 3D GEOMETRY CONTROL 论文阅读笔记

2025-03-19 12:00:00 1233 1

原创 论文阅读笔记——Adapter,AdapterFusion,AdapterDrop

Adapter,AdapterFusion,AdapterDrop 论文阅读笔记

2025-03-18 12:00:00 1400 1

原创 论文阅读笔记——BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 论文阅读笔记

2025-03-17 12:00:00 1120 1

原创 论文阅读笔记——ADALORA: ADAPTIVE BUDGET ALLOCATION FOR PARAMETER-EFFICIENT FINE-TUNING

ADALORA: ADAPTIVE BUDGET ALLOCATION FOR PARAMETER-EFFICIENT FINE-TUNING 论文阅读笔记

2025-03-16 15:08:05 1144 1

原创 论文阅读笔记——QLORA: Efficient Finetuning of Quantized LLMs

QLORA: Efficient Finetuning of Quantized LLMs 论文阅读笔记

2025-03-15 19:33:21 1558 3

原创 论文阅读笔记——LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS

LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS 论文阅读笔记

2025-03-14 12:44:03 1299 1

原创 论文阅读笔记——OpenVLA: An Open-Source Vision-Language-Action Model

OpenVLA: An Open-Source Vision-Language-Action Model 论文阅读笔记

2025-03-09 13:25:19 1192 1

原创 论文阅读笔记——Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations 论文阅读笔记

2025-03-08 13:03:54 1128 1

原创 论文阅读笔记——π0: A Vision-Language-Action Flow Model for General Robot Control

π0: A Vision-Language-Action Flow Model for General Robot Control 论文阅读笔记

2025-03-06 21:01:13 1442 1

原创 论文阅读笔记——Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware 论文阅读笔记

2025-03-05 21:20:12 1178 1

原创 论文阅读笔记——EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

EnerVerse: Envisioning EmbodiedFutureSpacefor RoboticsManipulation 论文阅读笔记

2025-03-03 20:10:08 1097 1

原创 论文阅读笔记——DexVLA,ChatVLA

DexVLA,ChatVLA 论文阅读笔记

2025-03-02 15:59:19 535 1

原创 论文阅读笔记——VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipula

VidMan: Exploiting Implicit Dynamics from VideoDiffusion Model for Effective Robot Manipulation 论文阅读笔记

2025-03-01 17:28:12 974 1

原创 论文阅读笔记——Prediction with Action: Visual Policy Learning via Joint Denoising Process

Prediction with Action: Visual Policy Learning via Joint Denoising Process论文阅读笔记

2025-02-28 20:07:35 242 1

原创 论文阅读笔记——AVID:Adapting Video Diffusion Models to World Models

AVID: Adapting Video Diffusion Models to World Models 论文阅读笔记

2025-02-26 23:11:44 1086 1

原创 运筹学——线性规划单纯形方法

统筹学的线性规划——单纯形方法详解

2025-02-25 21:37:59 1204

原创 论文阅读笔记——DiT

本文探索了一类新的基于 Transformer 的扩散模型 Diffusion Transformers (DiTs)。本文训练 latent diffusion models 时,使用 Transformer 架构替换常用的 UNet 架构,且 Transformer 作用于 latent patches 上。

2025-02-23 14:14:11 390 1

原创 论文阅读笔记——ViT

将输入图像通过可选的 ResNet 预处理阶段提取特征,然后将图像分割成 patch 并嵌入到 Transformer 可处理的序列中。通过 Transformer 编码器对序列进行编码后,根据分类器的类型(如 token、gap 等)提取特征表示,最后通过全连接层输出分类结果。该模型支持添加类别 token、全局平均池化等操作,并可选择是否在 Transformer 前使用 ResNet 进行特征提取。

2025-02-22 23:26:44 1028 3

空空如也

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除