Latest Articles for Safety

A new method enhances communication skills of language agents.

A new method enhances safety features in multimodal AI systems without extensive training.

Exploring the key traits and challenges of developing reliable AI systems.

Gillian-Rust offers a novel way to verify unsafe Rust code effectively.

A study on the performance and evaluation methods of large language models.

Two new algorithms enhance robot perception and ensure safety in various environments.

An overview of formal methods for designing safe autonomous systems.

New techniques enable safer decision-making in reinforcement learning through human expert guidance.

ALERT benchmark assesses safety risks in language models to improve their responses.

A review of datasets focused on enhancing LLM safety.

Cendol enhances language tech for Indonesia's diverse languages and cultures.

An overview of creating effective reward functions in self-driving cars.

New control method offers a realistic approach for improved system safety and efficiency.

New framework aims to enhance drug dosage recommendations during pregnancy.

New techniques aim to maintain safety in unpredictable control systems with limited data.

Measuring robustness and safety in cyber-physical systems under sensor threats.

Robotic systems are shaping the future of neurosurgery, improving safety and precision.

Study reveals how models respond to gibberish prompts and implications for safety.

Exploring the responsible use of generative AI technology in various fields.

A new approach to safety analysis using piecewise stochastic barrier functions.

AI aids in creating drugs to treat brain-related conditions by crossing the blood-brain barrier.

Examining the impact of Ethereum's inactivity leak mechanism on network safety.

Two new treatments for Alzheimer's show promise but raise safety concerns.

A comprehensive study on treatments for age-related eye diseases in older adults in China.

A new magnetic mechanism enhances rehabilitation robots for smoother patient recovery.

AI tools show potential but face significant safety concerns for mental health support.

Examining Twitter discussions reveals evolving public views on COVID-19 vaccines.

PARDEN improves safety in language models against harmful responses.

New methods improve the creation of distributed protocols for reliable computing.

A method to improve safety while maintaining performance in large language models.

Examining the risks and opportunities of open-source generative AI technology.

New benchmark assesses toxicity in large language models across various languages.

Exploring the impact of smart cameras on privacy and relationships.

Exploring counterfactual harm constraints for safer decision-making in AI.

This article examines the methods for creating safe autonomous vehicles.

Exploring the regulatory landscape of generative AI and its implications.

AI is reshaping manufacturing with efficiency, quality control, and predictive maintenance.

A method for verifying safety in self-driving cars and drones using neural networks.

A study investigates e-scooter user behavior in various traffic scenarios.

Study focuses on how robots can handle conflicts and communicate effectively with users.