Localizing and Editing the Goal Representation of a Vision-Language-Action Model
cs.RO
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
- Goal Misgeneralization in Deep Reinforcement Learning
- Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
- Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress
- Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies
- SAFE: Multitask Failure Detection for Vision-Language-Action Models
- Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
- ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies
- VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models
- SAFECAST: Robust Failure Detection for VLA Policies with Contrast-Set Training and Calibration
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture
- Emergent World Representations in OpenVLA
- What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies
- Decoding Task Progress from VLA Representations
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation