Researchers have replicated an earlier study on AI efficiency assessment using Floating Point Operations (FLOPs). They found that while FLOPs can be u...
Researchers developed a controlled test to evaluate the performance of large language models (LLMs) in medical reasoning. They created synthetic patie...
Researchers have introduced a new challenge called The Unwritten Benchmark to test multimodal machine learning models' ability to perform abstract per...
Researchers propose a new approach to communication in multi-agent reinforcement learning. Instead of communicating at every timestep or using a binar...
A comparative review of global AI regulations for fairness and ethics in high-risk use cases has been published. The study maps risk classification tr...
AI safety researchers argue that the field has focused too much on technical alignment and regulation of generative AI. They claim that excessive reli...
Researchers argue that current methods for evaluating AI moral reasoning are incomplete. They focus on whether models align with human values, but neg...
The authors provide a comprehensive review of the history and development of computational belief change. They trace its evolution from Doyle's taxono...
The authors argue that current approaches to AI governance, which rely on jurisdiction-specific laws and policies, create a fragmented regulatory land...
Researchers argue that neural networks used for constraint satisfaction problems must be integrated with symbolic methods to ensure correctness. They ...
The machine learning community has a large presence in academic publishing, but reviewers often have negative experiences. Researchers propose using a...
Researchers used data from over 11,000 adolescents in a large study to compare different methods for predicting when young people might start using su...