Image de couverture de livre

Bring the Apple, Not the Sofa: Impact of Irrelevant Context in Embodied AI Commands on VLA Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pugacheva, Daria, Moskalenko, Andrey, Shepelev, Denis, Kuznetsov, Andrey, Shakhuro, Vlad, Tutubalina, Elena
Format:	Preprint
Publié:	2025
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space
par: Zinkovich, Viktoriia, et autres
Publié: (2025)

RoboBenchMart: Benchmarking Robots in Retail Environment
par: Soshin, Konstantin, et autres
Publié: (2025)

BREPS: Bounding-Box Robustness Evaluation of Promptable Segmentation
par: Moskalenko, Andrey, et autres
Publié: (2026)

RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation
par: Antonov, Anton, et autres
Publié: (2024)

TETRIS: Towards Exploring the Robustness of Interactive Segmentation
par: Moskalenko, Andrey, et autres
Publié: (2024)

BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment
par: Sakhovskiy, Andrey, et autres
Publié: (2025)

Mind and Motion Aligned: A Joint Evaluation IsaacSim Benchmark for Task Planning and Low-Level Policies in Mobile Manipulation
par: Kachaev, Nikita, et autres
Publié: (2025)

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
par: Zheng, Zihao, et autres
Publié: (2026)

TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models
par: Im, Hokyun, et autres
Publié: (2025)

Embodied Supervision: Haptic Display of Automation Command to Improve Supervisory Performance
par: Gilbert, Alia, et autres
Publié: (2024)

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
par: Liu, Jiahang, et autres
Publié: (2025)

X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
par: Li, Boyu, et autres
Publié: (2026)

Vintix: Action Model via In-Context Reinforcement Learning
par: Polubarov, Andrey, et autres
Publié: (2025)

TrackVLA: Embodied Visual Tracking in the Wild
par: Wang, Shaoan, et autres
Publié: (2025)

RynnEC: Bringing MLLMs into Embodied World
par: Dang, Ronghao, et autres
Publié: (2025)

Concept: Dynamic Risk Assessment for AI-Controlled Robotic Systems
par: Grimmeisen, Philipp, et autres
Publié: (2024)

Think Proprioceptively: Embodied Visual Reasoning for VLA Manipulation
par: Wang, Fangyuan, et autres
Publié: (2026)

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
par: Borisiuk, Anna, et autres
Publié: (2026)

MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption
par: Li, Chen, et autres
Publié: (2025)

ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context
par: Jang, Huiwon, et autres
Publié: (2025)

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
par: Zheng, Zihao, et autres
Publié: (2026)

UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models
par: Zhang, Qiyao, et autres
Publié: (2026)

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
par: Yang, Yi, et autres
Publié: (2025)

Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning
par: Liang, Wenlong, et autres
Publié: (2025)

Gemini Robotics: Bringing AI into the Physical World
par: Gemini Robotics Team, et autres
Publié: (2025)

UNCOM: Zero-shot Context-Aware Command Understanding for Tabletop Scenarios
par: Gonzalez, Antonio Galiza Cerdeira, et autres
Publié: (2024)

Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion
par: Li, Zhuo, et autres
Publié: (2025)

TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation
par: Zhou, Hanyu, et autres
Publié: (2026)

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
par: Zheng, Ruijie, et autres
Publié: (2024)

ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
par: Chu, Zedong, et autres
Publié: (2026)

Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation
par: Zhang, Zhilong, et autres
Publié: (2026)

Modeling the Mental World for Embodied AI: A Comprehensive Review
par: Liu, Biyuan, et autres
Publié: (2025)

VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
par: Li, Wenhao, et autres
Publié: (2026)

Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI
par: Ni, Fei, et autres
Publié: (2025)

$π$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation
par: Tucker, Johnathan, et autres
Publié: (2026)

HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing
par: Gubernatorov, Konstantin, et autres
Publié: (2026)

SABER: A Scalable Action-Based Embodied Dataset for Real-World VLA Adaptation
par: Menga, Narsimha, et autres
Publié: (2026)

Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
par: Liang, Zhixuan, et autres
Publié: (2025)

A Universal Large Language Model -- Drone Command and Control Interface
par: Ramos-Silva, Javier N., et autres
Publié: (2026)

EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development
par: Zhou, Xueyang, et autres
Publié: (2026)