zzqdeco ~/blog

#Deep Reading

共 33 篇 · 第 2 / 4 页
tags Deep Reading 33 Paper Reading 24 Code Reading 16 Computer Vision 12 Generative AI 5 Recommendation System 5 3D Generation 4 Agentic RL 3
还有 96 个标签 →
Deep Learning 3 Diffusion Models 3 Engineering 3 Image-to-3D 3 Knowledge Graph 3 Reinforcement Learning 3 Text-to-3D 3 3D Scene Generation 2 3D Scene Synthesis 2 Asynchronous RL 2 Computer Graphics 2 Graphics 2 NeRF 2 Optimization 2 RAG 2 Ranking 2 Systems 2 Two-Tower 2 Workflow 2 YouTube 2 3D Assets 1 3D Gaussian Splatting 1 3D Reconstruction 1 3D Scene Editing 1 3D Scene Modeling 1 3D Vision 1 Agent Memory 1 AI 1 AI Agents 1 Alibaba 1 ANN 1 Authorization 1 CAD Alignment 1 CAD Retrieval 1 Claude Code 1 Codex 1 Cold Start 1 Content Provenance 1 Context Engineering 1 Credit Assignment 1 CTR Prediction 1 Cypher 1 Database Internals 1 DeepSeek 1 Einops 1 Fourier Convolution 1 Generative Models 1 Generative Recommenders 1 Git 1 Graph Database 1 Graphiti 1 HSTU 1 Hybrid Search 1 Image Inpainting 1 Image Watermarking 1 Knowledge Augmented Generation 1 LLM Inference 1 LLM Post-Training 1 LLM Reliability 1 Long-Horizon RL 1 Loss Landscape 1 Machine Learning 1 Meta 1 Multi-Task Learning 1 Multimodal LLM 1 Multitask Learning 1 Neo4j 1 Notes 1 OpenFGA 1 OpenSPG 1 Pose Estimation 1 Python 1 Qwen 1 ReBAC 1 Rectified Flow 1 Referring Segmentation 1 Search 1 Search Engine 1 Security 1 Semi-Autoregressive Generation 1 Sequential Recommendation 1 Single-view Reconstruction 1 Speculative Decoding 1 Survey 1 System Design 1 Tensor Programming 1 Theory 1 Training Systems 1 Tutorial 1 User Interest Modeling 1 Vector Search 1 Vespa 1 Visual Grounding 1 Works 1 Zanzibar 1 Zep 1

2026

2026.07

  1. Einops 论文精读：Einstein-like Pattern Language、张量形状语义与跨框架执行

    从 ICLR 2022 论文与 einops 0.8.2 源码双线精读 rearrange、reduce、repeat、pack、einsum、Pattern Parser、Transformation Recipe 与多后端执行机制

    Deep ReadingPaper ReadingPython +4

  2. Qwen3-VL-Seg 论文精读：开放世界指代分割、Box-Guided Decoder 与 SA1B-ORS

    精读 Qwen3-VL-Seg 如何将 Qwen3-VL 的开放世界框定位先验转成像素级掩码，并通过轻量解码器、SA1B-ORS 和 ORS-Bench 扩展开放世界指代分割

    Deep ReadingPaper ReadingComputer Vision +4

  3. SIM 论文精读：搜索式用户兴趣建模、终身行为序列与工业 CTR 预测

    精读阿里 SIM 如何通过两级搜索、用户行为树、长序列检索和实时预测系统改造，在 CTR 预测中建模最长 54000 的终身用户行为序列

    Deep ReadingPaper ReadingRecommendation System +4

  4. TripoSG 论文精读：大规模 Rectified Flow、SDF VAE 与高保真 3D 形状生成

    精读 TripoSG 如何通过 Rectified Flow Transformer、CLIP+DINOv2 条件注入、SDF/normal/eikonal 混合监督和 2M 高质量数据构建实现高保真 image-to-3D 形状生成

    Deep ReadingPaper Reading3D Generation +4

  5. SF3D 论文精读：0.5 秒 3D Mesh 重建、UV 展开与光照解耦

    精读 SF3D 如何基于 LRM/TripoSR 改造快速单图 3D 重建，通过增强 Transformer、DMTet、快速 UV 展开、材质估计和光照解耦生成可用 textured mesh

    Deep ReadingPaper Reading3D Reconstruction +4

  6. AssetGen 论文精读：可部署 3D 资产生成、MeshGen/TextureGen 与交互式低延迟系统

    精读 AssetGen 如何通过两阶段 MeshGen、GPU 几何处理、UV 展开、法线烘焙、多视角 TextureGen、蒸馏和流水线优化实现 30 秒级可部署 3D 资产生成

    Deep ReadingPaper Reading3D Generation +4

  7. OpenFGA 精读：Zanzibar 关系授权模型、ReBAC 建模语言与生产级细粒度权限系统

    从 Zanzibar 论文与 OpenFGA 官方实现双线精读关系元组、授权模型、Check/Expand/ListObjects、条件元组、CLI 测试、存储部署与工程落地边界

    Deep ReadingOpenFGAAuthorization +5

  8. TRELLIS.2 论文精读：O-Voxel、Sparse Compression VAE 与 4B 参数 3D 生成模型

    精读 Native and Compact Structured Latents for 3D Generation 如何通过 O-Voxel、稀疏压缩 VAE、PBR 材质建模与大规模 flow matching 实现高质量 3D 资产生成

    Deep ReadingPaper Reading3D Generation +4

  9. Vespa 入门教程：从本地搜索应用到向量检索、混合排序与 RAG 基础

    系统讲解 Vespa 的应用包、Schema、YQL、文档写入、BM25、向量近邻、混合检索、排序配置和本地/云端部署入门流程

    Deep ReadingVespaSearch Engine +4
2026.06

  1. Layout2Scene 论文精读：3D 语义布局引导、混合场景表示与几何/外观扩散先验

    精读 Layout2Scene 如何通过 3D semantic layout、对象 Gaussian、背景 polygon、语义几何扩散和语义几何外观扩散实现可控 3D 场景生成

    Deep ReadingPaper Reading3D Scene Generation +4