{"ID":2921868,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T21:25:28.92412553Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01458","arxiv_id":"2606.01458","title":"LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World","abstract":"Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleoperation demonstrations. VLA policies fine-tuned in simulators have, until now, failed to transfer effectively in humanoid loco-manipulation tasks. We present LEGS (Loco-manipulation via Embodied Gaussian Splatting), a hybrid simulator that composites a mesh foreground (robot, objects, props) over a photorealistic 3D Gaussian Splatting (3DGS) background reconstructed from a handheld scene capture. LEGS uses a procedural motion-primitive generator to synthesize labeled demonstrations at scale without human teleoperation, and a deterministic two-stage color calibration to align the rendered 3DGS image to the robot's deployment camera. On a Unitree G1 humanoid robot, across three pick-and-place tasks of increasing whole-body difficulty and three VLA backbones (psi_0, pi_0.5, GR00T N1.6), a policy trained purely on LEGS data matches or exceeds one trained on human teleoperation demos on every experiment. It also outperforms a mesh-only simulation baseline that ablates the effect of the 3DGS background, showing that photorealistic rendering is a key enabler for synthetic data transfer. Humanoid motion is recorded independently of scene appearance in LEGS, allowing the same auto-generated demonstrations to be re-rendered under new backgrounds and object meshes--covering a new scene at more than 15x lower cost than teleoperation--to augment training data for robustness to scene variations. Under combined object-and-scene appearance shift, the policy trained on re-rendered LEGS-AUG data maintains task success while the baseline trained on teleoperation data fails entirely. Our project page is located at https://legsvla.github.io/.","short_abstract":"Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleoperation demonstrations. VLA policies fine-tuned in simulators have, until now, failed to transfer effectively in humanoid loco-manipulation tasks. We present LEGS (Loco-...","url_abs":"https://arxiv.org/abs/2606.01458","url_pdf":"https://arxiv.org/pdf/2606.01458v1","authors":"[\"Hojune Kim\",\"Timothy Chen\",\"Jiankai Sun\",\"Lars W. Osterberg\",\"Qianzhong Chen\",\"Ke Wang\",\"Mac Schwager\"]","published":"2026-05-31T21:36:02Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}