Image de couverture de livre

What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Jiachen, Nie, Junnan, Lao, Junyi, Cheng, Wei, Liu, Chenghao, Jiang, Jiaxin, Huang, Songfang
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking
par: Nie, Junnan, et autres
Publié: (2026)

Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation
par: Xu, Siyu, et autres
Publié: (2025)

FASTER: Rethinking Real-Time Flow VLAs
par: Lu, Yuxiang, et autres
Publié: (2026)

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
par: Zhao, Jianchao, et autres
Publié: (2026)

TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models
par: Liu, Chenghao, et autres
Publié: (2025)

Running VLAs at Real-time Speed
par: Ma, Yunchao, et autres
Publié: (2025)

SITCOM: Scaling Inference-Time COMpute for VLAs
par: Saxena, Ayudh, et autres
Publié: (2025)

How Do VLAs Effectively Inherit from VLMs?
par: Zhang, Chuheng, et autres
Publié: (2025)

Differentiate-and-Inject: Enhancing VLAs via Functional Differentiation Induced by In-Parameter Structural Reasoning
par: Hou, Jingyi, et autres
Publié: (2026)

Quality-focused Active Adversarial Policy for Safe Grasping in Human-Robot Interaction
par: Li, Chenghao, et autres
Publié: (2025)

Shallow-π: Knowledge Distillation for Flow-based VLAs
par: Jeon, Boseong, et autres
Publié: (2026)

Primitive Subspaces Mediate Few-Shot Transfer in VLAs
par: Singh, Anya, et autres
Publié: (2026)

VLAs are Confined yet Capable of Generalizing to Novel Instructions
par: Li, Quanyi
Publié: (2025)

Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds
par: Choi, Andrew, et autres
Publié: (2026)

Policy Contrastive Decoding for Robotic Foundation Models
par: Wu, Shihan, et autres
Publié: (2025)

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
par: Hancock, Asher J., et autres
Publié: (2025)

Notes-to-Self: Scratchpad Augmented VLAs for Memory Dependent Manipulation Tasks
par: Haresh, Sanjay, et autres
Publié: (2026)

How VLAs (Really) Work In Open-World Environments
par: Rasouli, Amir, et autres
Publié: (2026)

cVLA: Towards Efficient Camera-Space VLAs
par: Argus, Max, et autres
Publié: (2025)

Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate
par: Yang, Chen, et autres
Publié: (2026)

What Can Robots Teach Us About Trust and Reliance? An interdisciplinary dialogue between Social Sciences and Social Robotics
par: Wacquez, Julien, et autres
Publié: (2025)

VLA-0: Building State-of-the-Art VLAs with Zero Modification
par: Goyal, Ankit, et autres
Publié: (2025)

mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
par: Pai, Jonas, et autres
Publié: (2025)

The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption
par: Duggan, Timothy, et autres
Publié: (2026)

Pyramid-Monozone Synergistic Grasping Policy in Dense Clutter
par: Li, Chenghao, et autres
Publié: (2024)

Do World Action Models Generalize Better than VLAs? A Robustness Study
par: Zhang, Zhanguang, et autres
Publié: (2026)

Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
par: Priyadershi, Abhinaw, et autres
Publié: (2026)

VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis
par: Zhang, Jiachen, et autres
Publié: (2026)

Beyond Binary Success: Sample-Efficient and Statistically Rigorous Robot Policy Comparison
par: Snyder, David, et autres
Publié: (2026)

Shoulder Range of Motion Rehabilitation Robot Incorporating Scapulohumeral Rhythm for Frozen Shoulder
par: Cho, Hyunbum, et autres
Publié: (2025)

What Foundation Models can Bring for Robot Learning in Manipulation : A Survey
par: Li, Dingzhe, et autres
Publié: (2024)

GRADE: Generating Realistic And Dynamic Environments for Robotics Research with Isaac Sim
par: Bonetto, Elia, et autres
Publié: (2023)

LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World
par: Kim, Hojune, et autres
Publié: (2026)

GUIDES: Guidance Using Instructor-Distilled Embeddings for Pre-trained Robot Policy Enhancement
par: Gao, Minquan, et autres
Publié: (2025)

Mask World Model: Predicting What Matters for Robust Robot Policy Learning
par: Lou, Yunfan, et autres
Publié: (2026)

Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
par: Niu, Jiahui, et autres
Publié: (2026)

When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
par: Fang, Yu, et autres
Publié: (2026)

Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation
par: Zhang, Xuening, et autres
Publié: (2026)

A Robotic Skill Learning System Built Upon Diffusion Policies and Foundation Models
par: Ingelhag, Nils, et autres
Publié: (2024)

Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots
par: Zhang, Yang, et autres
Publié: (2025)