SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Paper
β’
2506.01844
β’
Published
β’
50
Mishig Davaadorj
mishig
AI & ML interests
NP-completeness, grammars, universality
Recent Activity
upvoted
a
paper
about 20 hours ago
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient
Robotics
new activity
6 days ago
deepseek-ai/DeepSeek-R1-0528:Summer or Winter?
updated
a Space
6 days ago
huggingface/inference-playground
Organizations
mishig's activity
upvoted
a
paper
about 20 hours ago
Summer or Winter?
π
π
71
61
#1 opened 6 days ago
by
andromeda0302
updated
a
Space
6 days ago
upvoted
an
article
9 days ago
Article
Interactive Tools for machine learning, deep learning, and math
By
β’
β’
40
reacted to
Kseniase's
post with π
10 days ago
Post
4202
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 π
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
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 π
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
upvoted
a
paper
11 days ago
upvoted
a
changelog
12 days ago
Changelog
AI-generated Abstract summaries on Hugging Face Papers
β’
65
published
a
changelog
13 days ago
Changelog
AI-generated Abstract summaries on Hugging Face Papers
β’
65
upvoted
a
changelog
13 days ago
Changelog
Filter by MCP compatibility available in HF Spaces
β’
70
updated
a
Space
13 days ago
published
a
changelog
13 days ago
Changelog
Filter by MCP compatibility available in HF Spaces
β’
70
updated
a
Space
19 days ago
published
a
Space
19 days ago
commented on
Falcon-Edge: A series of powerful, universal, fine-tunable 1.58bit language models.
20 days ago
lets go
upvoted
an
article
20 days ago
Article
Falcon-Edge: A series of powerful, universal, fine-tunable 1.58bit language models.
By
and 9 others
β’
β’
32