Entity Pages

Files

• bolmo-2025.md - Fully open byte-level LM family produced by byteifying subword LMs.
• chatts-2024.md - Time-series multimodal LLM trained from synthetic time-series/text data.
• dinov3-2025.md - Self-supervised vision foundation model suite.
• eidos-2026.md - Time-series foundation model family based on latent-space predictive learning.
• h-net-2025.md - Hierarchical sequence model with learned dynamic chunking.
• lejepa-2025.md - JEPA objective combining predictive loss with SIGReg.
• timeomni-1-2026.md - Time-series reasoning model and TSR-Suite.
• timeomni-vl-2026.md - Vision-centric time-series understanding/generation framework.
• tuna-2-2026.md - Pixel-space unified multimodal model.
• vl-jepa-2025.md - Vision-language JEPA system.