Image de couverture de livre

Can AI Perceive Physical Danger and Intervene?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jindal, Abhishek, Kalashnikov, Dmitry, Hofer, R. Alex, Chang, Oscar, Garikapati, Divya, Majumdar, Anirudha, Sermanet, Pierre, Sindhwani, Vikas
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Generating Robot Constitutions & Benchmarks for Semantic Safety
par: Sermanet, Pierre, et autres
Publié: (2025)

SciFi-Benchmark: Leveraging Science Fiction To Improve Robot Behavior
par: Sermanet, Pierre, et autres
Publié: (2025)

Predictive Red Teaming: Breaking Policies Without Breaking Robots
par: Majumdar, Anirudha, et autres
Publié: (2025)

Autonomous Vehicles: Evolution of Artificial Intelligence and Learning Algorithms
par: Garikapati, Divya, et autres
Publié: (2024)

Deceptive Risk Minimization: Out-of-Distribution Generalization by Deceiving Distribution Shift Detectors
par: Majumdar, Anirudha
Publié: (2025)

FTA generation using GenAI with an Autonomy sensor Usecase
par: Shetiya, Sneha Sudhir, et autres
Publié: (2024)

Thinking Forward and Backward: Effective Backward Planning with Large Language Models
par: Ren, Allen Z., et autres
Publié: (2024)

How Confident are Video Models? Empowering Video Models to Express their Uncertainty
par: Mei, Zhiting, et autres
Publié: (2025)

Red Teaming AI Red Teaming
par: Majumdar, Subhabrata, et autres
Publié: (2025)

Learning to Intervene on Concept Bottlenecks
par: Steinmann, David, et autres
Publié: (2023)

The Hidden Dangers of Browsing AI Agents
par: Mudryi, Mykyta, et autres
Publié: (2025)

Gen AI in Automotive: Applications, Challenges, and Opportunities with a Case study on In-Vehicle Experience
par: Shinde, Chaitanya, et autres
Publié: (2025)

STEER: Flexible Robotic Manipulation via Dense Language Grounding
par: Smith, Laura, et autres
Publié: (2024)

A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions
par: Shorinwa, Ola, et autres
Publié: (2024)

Technical Requirements for Halting Dangerous AI Activities
par: Barnett, Peter, et autres
Publié: (2025)

Evaluating Gemini Robotics Policies in a Veo World Simulator
par: Gemini Robotics Team, et autres
Publié: (2025)

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
par: Mei, Zhiting, et autres
Publié: (2025)

World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty
par: Mei, Zhiting, et autres
Publié: (2025)

A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
par: Dwibedi, Debidatta, et autres
Publié: (2024)

Flash STU: Fast Spectral Transform Units
par: Liu, Y. Isabel, et autres
Publié: (2024)

The AI Risk Spectrum: From Dangerous Capabilities to Existential Threats
par: Grey, Markov, et autres
Publié: (2025)

Physically Grounded Vision-Language Models for Robotic Manipulation
par: Gao, Jensen, et autres
Publié: (2023)

Fighting AI with AI: Leveraging Foundation Models for Assuring AI-Enabled Safety-Critical Systems
par: Mavridou, Anastasia, et autres
Publié: (2025)

Clawed and Dangerous: Can We Trust Open Agentic Systems?
par: Chen, Shiping, et autres
Publié: (2026)

V-CEM: Bridging Performance and Intervenability in Concept-based Models
par: De Santis, Francesco, et autres
Publié: (2025)

Can LLMs Perceive Time? An Empirical Investigation
par: Garikaparthi, Aniketh
Publié: (2026)

Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?
par: Karkevandi, Mohammad Bahrami, et autres
Publié: (2024)

ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
par: Yang, Linyi, et autres
Publié: (2025)

Temporal Reasoning in AI systems
par: Sharma, Abhishek
Publié: (2025)

YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks
par: Bandyopadhyay, Saptarashmi, et autres
Publié: (2025)

Identifying Intervenable and Interpretable Features via Orthogonality Regularization
par: Miller, Moritz, et autres
Publié: (2026)

Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail Prediction
par: Basu, Sagnik, et autres
Publié: (2025)

From Ethical Declarations to Provable Independence: An Ontology-Driven Optimal-Transport Framework for Certifiably Fair AI Systems
par: Bhattacharya, Sukriti, et autres
Publié: (2025)

IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning
par: Hoque, Ryan, et autres
Publié: (2024)

RT-H: Action Hierarchies Using Language
par: Belkhale, Suneel, et autres
Publié: (2024)

Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators
par: Badithela, Apurva, et autres
Publié: (2025)

Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning
par: Sehanobish, Arijit, et autres
Publié: (2024)

Key Safety Design Overview in AI-driven Autonomous Vehicles
par: Vyas, Vikas, et autres
Publié: (2024)

Concept Layers: Enhancing Interpretability and Intervenability via LLM Conceptualization
par: Bidusa, Or Raphael, et autres
Publié: (2025)

LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer
par: Zha, Lihan, et autres
Publié: (2026)