20260625:很多新内容

This commit is contained in:
2026-06-25 14:08:47 +08:00
parent 91fac5b6fc
commit 6021dea160
375 changed files with 19263 additions and 251 deletions

41
concepts/vla-jepa.md Normal file
View File

@@ -0,0 +1,41 @@
---
title: "VLA-JEPA (模型)"
created: 2026-06-24
updated: 2026-06-24
type: concept
tags: ["vla", "jepa", "world-model", "robot-learning"]
sources:
- "[[vla-jepa-2026]]"
---
# VLA-JEPA
VLA-JEPA 是将 JEPA 范式引入 Vision-Language-Action 模型的预训练框架。核心思想:通过 leakage-free state prediction 在 latent space 学习动作相关的动态抽象。
## 架构
- VLM BackboneQwen3-VL-2B
- Latent World ModelV-JEPA2 encoder (frozen target) + autoregressive Transformer predictor
- Action HeadConditional Flow-Matching
## 关键设计原则
1. Target encoder 从未来帧产生 latent target → 仅作监督目标
2. Student 仅见当前观察 → 消除信息泄漏
3. Latent space 预测(非 pixel space→ 鲁棒于外观变化
## 训练流程
两阶段简化为JEPA Pretraining → Action-Head Fine-tuning
vs 传统 latent-action 方法的多阶段流水线)
## 性能
LIBERO 平均 98.2%SOTASimplerEnv 领先,数据效率远超对比方法。
## 参考
- [[vla-jepa-2026]]
- [[jepa]]
- [[vla-vision-language-action]]
- [[leakage-free-state-prediction]]
- [[latent-world-model]]