Image de couverture de livre

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Torres-Fonseca, Josue, Deng, Naihao, Dai, Yinpei, Storks, Shane, Zhang, Yichi, Mihalcea, Rada, Kennington, Casey, Chai, Joyce
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rethinking Table Instruction Tuning
par: Deng, Naihao, et autres
Publié: (2025)

Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions
par: Deng, Naihao, et autres
Publié: (2025)

One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety
par: Arif, Samee, et autres
Publié: (2026)

Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation
par: Dai, Yinpei, et autres
Publié: (2023)

RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning
par: Dai, Yinpei, et autres
Publié: (2024)

AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies
par: Dai, Yinpei, et autres
Publié: (2025)

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
par: Xi, Jiajun, et autres
Publié: (2024)

Benchmarking and Improving LLM Robustness for Personalized Generation
par: Okite, Chimaobi, et autres
Publié: (2025)

Unsupervised, Bottom-up Category Discovery for Symbol Grounding with a Curious Robot
par: Henry, Catherine, et autres
Publié: (2024)

DOTRAG: Retrieval-Time Reasoning Along Paths
par: Moore, Larnell, et autres
Publié: (2026)

CliniDial: A Naturally Occurring Multimodal Dialogue Dataset for Team Reflection in Action During Clinical Operation
par: Deng, Naihao, et autres
Publié: (2025)

Safety-Conscious Pushing on Diverse Oriented Surfaces with Underactuated Aerial Vehicles
par: Hui, Tong, et autres
Publié: (2024)

The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models
par: Arif, Samee, et autres
Publié: (2026)

Safety Assurance for Quadrotor Kinodynamic Motion Planning
par: Tavoulareas, Theodoros, et autres
Publié: (2025)

Safety Aware Task Planning via Large Language Models in Robotics
par: Khan, Azal Ahmad, et autres
Publié: (2025)

Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors
par: Wang, Jian, et autres
Publié: (2025)

Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning
par: Li, Siyuan, et autres
Publié: (2024)

LUCid: Redefining Relevance For Lifelong Personalization
par: Okite, Chimaobi, et autres
Publié: (2026)

Instantaneous Planning, Control and Safety for Navigation in Unknown Underwater Spaces
par: Karthik, Veejay, et autres
Publié: (2026)

Occlusion-Aware Contingency Safety-Critical Planning for Autonomous Driving
par: Zheng, Lei, et autres
Publié: (2025)

Safety Evaluation of Motion Plans Using Trajectory Predictors as Forward Reachable Set Estimators
par: Chakraborty, Kaustav, et autres
Publié: (2025)

The Use of Gaze-Derived Confidence of Inferred Operator Intent in Adjusting Safety-Conscious Haptic Assistance
par: Webb, Jeremy D., et autres
Publié: (2025)

Safety2Drive: Safety-Critical Scenario Benchmark for the Evaluation of Autonomous Driving
par: Li, Jingzheng, et autres
Publié: (2025)

SPOC: Safety-Aware Planning Under Partial Observability And Physical Constraints
par: Kim, Hyungmin, et autres
Publié: (2026)

Enabling Safety for Aerial Robots: Planning and Control Architectures
par: Naveed, Kaleb Ben, et autres
Publié: (2025)

Safety-Oriented Dynamic Path Planning for Automated Vehicles
par: Emam, Mostafa, et autres
Publié: (2025)

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models
par: Lv, Qi, et autres
Publié: (2024)

Exposure Conscious Path Planning for Equal Exposure Corridors
par: Hamzezadeh, Eugene T., et autres
Publié: (2024)

S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles
par: Wang, Xiao, et autres
Publié: (2024)

Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language Models
par: Gan, Rui, et autres
Publié: (2025)

Balancing Safety and Optimality in Robot Path Planning: Algorithm and Metric
par: Arora, Jatin Kumar, et autres
Publié: (2025)

ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments
par: Kim, Taewoong, et autres
Publié: (2024)

Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties
par: Yu, Keunwoo Peter, et autres
Publié: (2023)

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
par: Li, Qi, et autres
Publié: (2026)

Discovering Properties of Inflectional Morphology in Neural Emergent Communication
par: Gilberti, Miles, et autres
Publié: (2025)

Full-Body Dynamic Safety for Robot Manipulators: 3D Poisson Safety Functions for CBF-Based Safety Filters
par: Wilkinson, Meg, et autres
Publié: (2026)

Multi-layered Safety of Redundant Robot Manipulators via Task-oriented Planning and Control
par: Jia, Xinyu, et autres
Publié: (2024)

Bridging the Gap: Regularized Reinforcement Learning for Improved Classical Motion Planning with Safety Modules
par: Goldsztejn, Elias, et autres
Publié: (2024)

Safety-critical Motion Planning for Collaborative Legged Loco-Manipulation over Discrete Terrain
par: Sombolestan, Mohsen, et autres
Publié: (2024)

Safety Meets Speed: Accelerated Neural MPC with Safety Guarantees and No Retraining
par: Wang, Kaikai, et autres
Publié: (2025)