AAA高老庄旺铺招租的个人博客

标签

Deep learning Generative models theory Diffusion models Generative models Diffusion Models Stable Diffusion Flux Reinforcement Learning DPO Flow Matching LLM Memory mechanism AI Companion 3D Vision Transformer Multi-modal Fusion Vision Transformer Register Tokens DINOv2 Self-Supervised Learning Computer Vision Multimodal Learning Fusion Cross-Attention NLP CLIP Contrastive Learning InfoNCE SigLIP Vision-Language Model BLIP-2 Q-Former LLaVA Visual Instruction Tuning Multimodal LLM Flamingo Chameleon Perceiver Resampler VQ-VAE Native Multimodal InternVL Qwen-VL Mamba State Space Model Multimodal Frontier Dreamer RSSM Model-based RL World Model JEPA V-JEPA Latent Space Generative Model Sora Genie Cosmos Video Generation PhysDreamer PhysGen NewtonGen Physics-Grounded GAIA-1 DriveDreamer OccWorld Vista Autonomous Driving 4D Generation WorldScore Embodied AI Frontier thinking 自我介绍

评论

AAA高老庄旺铺招租

欢迎来到我的博客

公告

欢迎来到AAA高老庄旺铺招租的猪舍~（昼伏夜出型）

最新文章

笔记｜世界模型（七）：前沿与统一视角——五条路线的收敛2026-04-06

笔记｜世界模型（六）：自动驾驶世界模型——从视频预测到占用预测2026-04-06

笔记｜世界模型（五）：物理化的视频生成——让模型理解牛顿定律2026-04-06

笔记｜世界模型（四）：视频生成即世界模拟——从 Sora 到 Genie 与 Cosmos2026-04-06

笔记｜世界模型（三）：JEPA——在嵌入空间预测世界2026-04-06

分类

Notes27
Tutorials15

标签

Contrastive Learning Video Generation 3D Vision Generative Model Model-based RL Fusion Transformer Multimodal Learning DPO LLaVA Register Tokens Cross-Attention Mamba Vision-Language Model Deep learning InfoNCE LLM AI Companion V-JEPA PhysDreamer Multi-modal Fusion PhysGen DriveDreamer SigLIP Generative models theory Multimodal LLM Perceiver Resampler Stable Diffusion Flamingo Cosmos Flow Matching Flux Physics-Grounded Self-Supervised Learning DINOv2 thinking BLIP-2 Q-Former Multimodal Frontier State Space Model

归档

四月 202620
八月 202520
七月 20252

网站资讯

文章数目 :

42

已运行时间 :

本站访客数 :

本站总访问量 :

最后更新时间 :

©2025 - 2026 By AAA高老庄旺铺招租

框架 Hexo|主题 Butterfly