Hamilton

Skydee9

AI & ML interests

None yet

Recent Activity

reacted to SaylorTwift's post with 👀 2 months ago

How do I test an LLM for my unique needs? If you work in finance, law, or medicine, generic benchmarks are not enough. This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models. https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md

repliedto SaylorTwift's post 2 months ago

reacted to Kseniase's post with 😎 2 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

None yet

reacted to SaylorTwift's post with 👀 2 months ago

Post

2816

How do I test an LLM for my unique needs?
If you work in finance, law, or medicine, generic benchmarks are not enough.
This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models.

https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md

1 reply

replied to SaylorTwift's post 2 months ago

Hello, can you please guide me through the steps to to clone a voice and use it for text to speech using Qwen3-TTS?

reacted to Kseniase's post with 😎 2 months ago

Post

9196

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 -> Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture (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 -> MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features (2307.12698)
Simultaneously interprets video data - dynamic elements (motion) and static details (content) - using a shared encoder

3. V-JEPA -> Revisiting Feature Prediction for Learning Visual Representations from Video (2404.08471)
Presents vision models trained by predicting future video features, without pretrained image encoders, text, negative sampling, or reconstruction

4. UI-JEPA -> UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity (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) -> A-JEPA: Joint-Embedding Predictive Architecture Can Listen (2311.15830)
Masks spectrogram patches with a curriculum, encodes them, and predicts hidden representations.

6. S-JEPA -> S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention (2403.11772)
Signal-JEPA is used in EEG analysis. It adds a spatial block-masking scheme and three lightweight downstream classifiers

7. TI-JEPA -> TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems (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

1 reply

Hamilton

AI & ML interests

Recent Activity

Organizations

Skydee9's activity