OpenHelix Robotics ORG

A paper list of multimodal VLAs

Official implementation of ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver.

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

OpenHelix: An Open-source Dual-System VLA Model for Robotic Manipulation

[AAAI-25] Cobra: Extending Mamba to Multi-modal Large Language Model for Efficient Inference

This repository summarizes recent advances in the VLA + RL paradigm and provides a taxonomic classification of relevant works.

RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark

Official implementation of Spatial-Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model [ICLR2026]

LLaVA-VLA: A Simple Yet Powerful Vision-Language-Action Model [ICRA 2026]

Official implementation of TrajBooster

🔥 The first open-sourced diffusion vision-langauge-action model. [ICLR 2026]

VLA-RFT: Vision-Language-Action Models with Reinforcement Fine-Tuning

[CVPR 2026] HiF-VLA: An efficient, bidirectional spatiotemporal expansion Vision-Language-Action Model

Official implementation of FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment

[ECCV 2026] Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.

No description.

No description.

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation

No description.

No description.