VL-JEPA: Joint Embedding Predictive Architecture for Vision-language Paper • 2512.10942 • Published Dec 11, 2025 • 64
view article Article SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data +7 danaaubakirova, andito, merve, ariG23498, fracapuano, loubnabnl, pcuenq, mshukor, cadene • Jun 3, 2025 • 373