Yann LeCun 澄清 DINO 与 V-JEPA 2.1 等 JEPA 系列的关系
LeCun 亲自解释 DINO、V-JEPA 2.1 和 LeJEPA 到底啥关系，分清方法研究和工程刷分，看懂 JEPA 这条线的必读。
Yann LeCun 在一条推文中梳理了 JEPA 系列研究的分类。他指出 DINO 技术上是一种 JEA，与其它 JEPA 模型的区别在抗坍缩准则和数据增广方案；Meta-FAIR 的 V-JEPA 2.1 则依赖大型专有数据集和大量算力做基准刷分。他强调 LeJEPA、LeWM 等学术方法是上游研究，不能与工程化的模型直接比较，前者是被资源方规模化后才会变成后者的基础。
Several comments: 1. image/video SSL methods differ by whether they use reconstruction or not. Joint embedding architectures Amy or may not have a predictor (JEA vs JEPA). They also differ by their anti-collapse method and data corruption/augmentation methods. 2. DINO *is* a kind of JEPA (technically a JEA). The difference with other JEPA models is the anti-collapse criterion (based on contrative clustering+ stopgradient/EMA), and the data augmentation scheme (image transformations, which is task specific), 3. V-JEPA 2.1, like DINO, is from Meta-FAIR (corporate lab), involved significant engineering teams, large/proprietary datasets, considerable computing resources, lots of fine-tuning, and number-pushing on many benchmarks. 4. Many JEPA papers are applications and/or fine-tuned versions of DINO, V-JEPA or I-JEPA. 5. LeJEPA, LeWM, and most other papers with "JEPA" in the title are *research* papers focused on the methodology, often done by students in academic labs, involving no engineering support, very little computing resources, and small/public training sets. They are generally tested on toy problems, simulated environments, or small/public benchmarks. 6. You simply cannot compare 5 with 2/3/4. 5 gives you ideas and new methods, not models. 2/3 give you well-engineered models, with lots of empirically validated tricks. Only rarely will 2/3 give you a new, well-principled method with room to spare. 5 give you empirical results on new applications. 7. What is published in 5 are methods that will eventually become like 2 and 3, whenever someone with resources picks it up and scales it. DO NOT CONFUSE UPSTREAM FOUNDATIONAL RESEARCH ON METHODS AND DOWNSTREAM SCALING -> ENGINEERING -> NUMBER PUSHING -> MODELS -> PRODUCTS. The former makes the rest possible, but it takes time. 💬 6 🔄 12 ❤️ 114 👀 8462 📊 24 ⚡
