Generative Representation Learning for Scalable Latent Tokenization
A generative tokenizer avoids representation collapse and reaches FID-50K 2.18 with JiT-L.
46
- Mentions · 7d0
- Mentions · 30d2
- All mentions2
- First seenOct 6, 2026
- Last mentioned11d ago
Timeline
2 articles · newest firstResearchers stretch LeCun's JEPA AI into a universal world model that works from physics to biology
Researchers unveil JEPA-Anything, a multi-predictor world model spanning physics through biology.
58
Appears with
- WebSSLai model · 1
- PhAI Labsorganization · 1
- Princeton Universityorganization · 1
- AMI Labsorganization · 1
- GPICproduct · 1
- University of Oxfordorganization · 1
- JiT-Lai model · 1
- V-JEPA 2ai model · 1
- C2S-Scale 27Bai model · 1
- DINOv2ai model · 1
- Stanford Universityorganization · 1
- JEPA-Anythingai model · 1
- Metaorganization · 1
- Metavendor · 1
- Gemmaai model · 1
- DINOai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.