Auditing Instruction-Trajectory Mismatches in Multimodal Robot Demonstrations
Simon Holk, Ryosuke Takanami, Tatsuya Matsushima, Yusuke Iwasawa, Yutaka Matsuo, Yueh-Hua Wu, Kei Ota
cs.RO, cs.LG
Submitted: 2026-08-08
Updated: 2026-08-11
Comments: Accepted for publication in IEEE Robotics and Automation Letters (RA-L). 8 pages, 3 figures, 7 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RT-1: Robotics Transformer for Real-World Control at Scale
- Octo: An Open-Source Generalist Robot Policy
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- CUPID: Curating Data your Robot Loves with Influence Functions
- Robot Data Curation with Mutual Information Estimators
- DataMIL: Selecting Data for Robot Imitation Learning with Datamodels
- SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning
- Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models
- CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision
- CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models
- Evaluating Uncertainty and Quality of Visual Language Action-enabled Robots
- Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning
- Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models
- LEMoN: Label Error Detection using Multimodal Neighbors
- Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictions
- When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
- Cosmos World Foundation Model Platform for Physical AI
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
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