VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model Paper • 2602.10098 • Published Feb 10 • 21
NVIDIA Nemotron v3 Collection Open, Production-ready Enterprise Models • 23 items • Updated 6 days ago • 328
view article Article Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models +1 loubnabnl, anton-l, davanstrien • Mar 20, 2024 • 114
Running on CPU Upgrade 253 The Synthetic Data Playbook: Generating Trillions of the Finest Tokens 📝 253 Visualize synthetic‑data experiments as an interactive bookshelf
view article Article Efficient MultiModal Data Pipeline +3 ariG23498, lusxvr, andito, sergiopaniego, pcuenq • Jul 8, 2025 • 72
IDEA-Research/grounding-dino-tiny Zero-Shot Object Detection • 0.2B • Updated May 12, 2024 • 535k • 103