SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos

arXiv:2606.02745 · cs.RO, cs.LG · Submitted 2026-06-01 · Read on arXiv

cs.RO, cs.LG

Submitted: 2026-06-01

Updated: 2026-10-13

Code: https://github.com/jaehyeon-son/SeeTraceAct

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• OpenVLA: An Open-Source Vision-Language-Action Model
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations
• MolmoAct: Action Reasoning Models that can Reason in Space
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• The Kinetics Human Action Video Dataset

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies