Helix: A Vision-Language-Action Model for Generalist Humanoid Control

Figure was founded with the ambition to change the world.

Helix: A Vision-Language-Action Model for Generalist Humanoid Control February 20, 2025 Introducing Helix We're introducing Helix, a generalist Vision-Language-Action (VLA) model that unifies perception, language understanding, and learned control to overcome multiple longstanding challenges in robotics. Helix is a series of firsts: Full-upper-body control : Helix is the first VLA to output high-rate continuous control of the entire humanoid upper body, including wrists, torso, head, and individual fingers. Multi-robot collaboration : Helix is the first VLA to operate simultaneously on two rob

saved by

• Saeejith Nair
• Hangyul Lyna Kim
• Yudhister Joel Kumar

related reading

• Learning dexterity | OpenAIopenai.com
• Abrar Anwarabraranwar.github.io
• A VLA with Open-World Generalizationpi.website
• Generalist - GEN-1: Scaling Embodied Foundation Models to Masterygeneralistai.com
• RT-2: Vision-Language-Action Modelsrobotics-transformer2.github.io
• Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
• Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Controlsteerable-policies.github.io
• State of Vision-Language-Action (VLA) Research at ICLR 2026 – Moritz Reussmbreuss.github.io
• A Steerable Model with Emergent Capabilitiespi.website
• The flavor of the bitter lesson for computer vision - Vincent Sitzmannvincentsitzmann.com
• [2602.10556] LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transferarxiv.org
• Precise Manipulation with Efficient Online RLpi.website