RoboHarness: A Simple Harness Outperforms VLA and World Action Models
cs.RO, cs.AI
Submitted: 2026-09-29
Updated: 2026-10-16
Comments: 18 pages, including references and appendices
Code: https://github.com/Wan-Video/Wan2.2
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
- Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
- MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting
- CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
- Galaxea Open-World Dataset and G0 Dual-System VLA Model
- OpenVLA: An Open-Source Vision-Language-Action Model
- Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge
- BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation
- Causal World Modeling for Robot Control
- G0.5: One Autoregressive Stream for Robot Reasoning and Action
- ASPIRE: Agentic /Skills Discovery for Robotics
- ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
- InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy
- Wan: Open and Advanced Large-Scale Video Generative Models
- RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation
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