Hugging Face's logo
ValerioL29's picture
2 16 84

ValerioL29

valeriol29
shtefcs's profile picture 21world's profile picture
·

AI & ML interests

Next-generation Information Retrieval models and systems.

Recent Activity

liked a model 1 day ago
onnx-community/siglip2-base-patch16-naflex-ONNX
liked a dataset 1 day ago
TAAC2025/TencentGR-10M
reacted to Kseniase's post with 🔥 4 months ago
12 Types of JEPA JEPA, or Joint Embedding Predictive Architecture, is an approach to building AI models introduced by Yann LeCun. It differs from transformers by predicting the representation of a missing or future part of the input, rather than the next token or pixel. This encourages conceptual understanding, not just low-level pattern matching. So JEPA allows teaching AI to reason abstractly. Here are 12 types of JEPA you should know about: 1. I-JEPA -> https://huggingface.co/papers/2301.08243 A non-generative, self-supervised learning framework designed for processing images. It works by masking parts of the images and then trying to predict those masked parts 2. MC-JEPA -> https://huggingface.co/papers/2307.12698 Simultaneously interprets video data - dynamic elements (motion) and static details (content) - using a shared encoder 3. V-JEPA -> https://huggingface.co/papers/2404.08471 Presents vision models trained by predicting future video features, without pretrained image encoders, text, negative sampling, or reconstruction 4. UI-JEPA -> https://huggingface.co/papers/2409.04081 Masks unlabeled UI sequences to learn abstract embeddings, then adds a fine-tuned LLM decoder for intent prediction. 5. Audio-based JEPA (A-JEPA) -> https://huggingface.co/papers/2311.15830 Masks spectrogram patches with a curriculum, encodes them, and predicts hidden representations. 6. S-JEPA -> https://huggingface.co/papers/2403.11772 Signal-JEPA is used in EEG analysis. It adds a spatial block-masking scheme and three lightweight downstream classifiers 7. TI-JEPA -> https://huggingface.co/papers/2503.06380 Text-Image JEPA uses self-supervised, energy-based pre-training to map text and images into a shared embedding space, improving cross-modal transfer to downstream tasks Find more types below 👇 Also, explore the basics of JEPA in our article: https://www.turingpost.com/p/jepa If you liked it, subscribe to the Turing Post: https://www.turingpost.com/subscribe
View all activity

Organizations

Incantor's profile picture