DyPES-VLA: cross-embodiment robot manipulation hits 98% on LIBERO
Junfeng Li · hf · 2026-08-07
DyPES-VLA learns shared dynamics priors and embodiment-specific control for cross-embodiment manipulation. It trains VLM with future prediction, and uses embodiment-specific MoE action head to output native actions without manual alignment. Achieves SOTA: 98.0% on LIBERO, 59.25% on RoboCasa-GR1, 89.02% on RoboTwin 2.0.
More from Embodied
- W2-VLA: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation — Yuhao Pan · 2026-08-07
- Robotic Arm Crosses Industries: Retires from Food Processing to Start Career in Electronics Assembly — viktor_vrp · 2026-08-07
- Non-YC Startup Pitching Kinematic World Model Data After First Month — andrew_n_carr · 2026-08-07
- ZecTrix Note 4: A 4.2-inch ESP32-S3 E-Ink Display with AI Voice Input — churchkey · 2026-08-07
- OpenAI Hardware Shipping Next Year to Achieve 'Personal AGI', Insider Claims — flowersslop · 2026-08-07
- Musk Forecasts TeraFab Compute: 25% for Optimus, 75% for Space AI — XFreeze · 2026-08-07