Buchumschlag

When Robots Should Say "I Don't Know": Benchmarking Abstention in Embodied Question Answering

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wu, Tao, Zhou, Chuhao, Zhao, Guangyu, Cao, Haozhi, Pu, Yewen, Yang, Jianfei
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries
von: Wu, Tao, et al.
Veröffentlicht: (2024)

REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?
von: Jiang, Chenxi, et al.
Veröffentlicht: (2025)

The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
von: Yeke, Doguhan, et al.
Veröffentlicht: (2026)

RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation
von: Chen, Xiangyu, et al.
Veröffentlicht: (2025)

World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty
von: Mei, Zhiting, et al.
Veröffentlicht: (2025)

AIR-Embodied: An Efficient Active 3DGS-based Interaction and Reconstruction Framework with Embodied Large Language Model
von: Qi, Zhenghao, et al.
Veröffentlicht: (2024)

MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents
von: Ding, Xin, et al.
Veröffentlicht: (2026)

When You Don't Know the Answer, Say So
Veröffentlicht: (2024)

When Robots Say No: The Empathic Ethical Disobedience Benchmark
von: Kuzmenko, Dmytro, et al.
Veröffentlicht: (2025)

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making
von: Liu, Jun, et al.
Veröffentlicht: (2026)

Hypo-paradoxical Linkages: Linkages That Should Move-But Don't
von: Shvalb, Nir, et al.
Veröffentlicht: (2025)

Extending Embodied Question Answering from Perception to Decision
von: Gong, Xicheng, et al.
Veröffentlicht: (2026)

Memory Centric Power Allocation for Multi-Agent Embodied Question Answering
von: Li, Chengyang, et al.
Veröffentlicht: (2026)

Trace-Focused Diffusion Policy for Multi-Modal Action Disambiguation in Long-Horizon Robotic Manipulation
von: Hu, Yuxuan, et al.
Veröffentlicht: (2026)

What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
von: Lee, Joosung, et al.
Veröffentlicht: (2026)

"Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation
von: Seffo, Amin, et al.
Veröffentlicht: (2025)

FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy
von: Zhang, Haochen, et al.
Veröffentlicht: (2026)

First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling
von: Davydov, Alexander, et al.
Veröffentlicht: (2024)

Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction
von: Wang, Xianhao, et al.
Veröffentlicht: (2026)

"Don't forget to put the milk back!" Dataset for Enabling Embodied Agents to Detect Anomalous Situations
von: Mullen Jr, James F., et al.
Veröffentlicht: (2024)

Physicists Don't Know What They're Talking About When They Say 'Order'
von: Arafat Gaspar Jiménez Gaistardo
Veröffentlicht: (2025)

Visual Environment-Interactive Planning for Embodied Complex-Question Answering
von: Lan, Ning, et al.
Veröffentlicht: (2025)

Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering
von: Dorbala, Vishnu Sashank, et al.
Veröffentlicht: (2024)

Don't double it: Efficient Agent Prediction in Occlusions
von: Rothenhäusler, Anna, et al.
Veröffentlicht: (2026)

R-Tuning: Instructing Large Language Models to Say `I Don't Know'
von: Zhang, Hanning, et al.
Veröffentlicht: (2023)

Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy
von: Ni, Minheng, et al.
Veröffentlicht: (2024)

Map-based Modular Approach for Zero-shot Embodied Question Answering
von: Sakamoto, Koya, et al.
Veröffentlicht: (2024)

Don't Yell at Your Robot: Physical Correction as the Collaborative Interface for Language Model Powered Robots
von: Zhang, Chuye, et al.
Veröffentlicht: (2024)

What You Don't Know Can Hurt You: How Well do Latent Safety Filters Understand Partially Observable Safety Constraints?
von: Kim, Matthew, et al.
Veröffentlicht: (2025)

Don't Just Search, Understand: Semantic Path Planning Agent for Spherical Tensegrity Robots in Unknown Environments
von: Zhang, Junwen, et al.
Veröffentlicht: (2025)

Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering
von: Ginting, Muhammad Fadhil, et al.
Veröffentlicht: (2025)

HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering
von: Li, Ji, et al.
Veröffentlicht: (2026)

Don't Get Stuck: A Deadlock Recovery Approach
von: Baldini, Francesca, et al.
Veröffentlicht: (2024)

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
von: Zhang, Jiefu, et al.
Veröffentlicht: (2026)

When Robots Say No: Temporal Trust Recovery Through Explanation
von: Webb, Nicola, et al.
Veröffentlicht: (2025)

$\mathbf{M^3A}$ Policy: Mutable Material Manipulation Augmentation Policy through Photometric Re-rendering
von: Li, Jiayi, et al.
Veröffentlicht: (2025)

EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering
von: Cheng, Kai, et al.
Veröffentlicht: (2024)

ConEQsA: Concurrent and Asynchronous Embodied Questions Scheduling and Answering
von: Wang, Haisheng, et al.
Veröffentlicht: (2025)

Explore until Confident: Efficient Exploration for Embodied Question Answering
von: Ren, Allen Z., et al.
Veröffentlicht: (2024)

Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation
von: Zuo, Kuangji, et al.
Veröffentlicht: (2026)