1193 stories curated by AInformed · page 28 of 50
Researchers introduced MAVEN (Modular Agentic Verification and Execution Network), a lightweight symbolic reasoning scaffold that helps AI agents use tools more reliably across different tasks. This could make AI assistants better at handling complex, multi-step problems.
Researchers found that AI models often prioritize globally dominant narratives over local cultural knowledge. They created a dataset to study this issue in Bengali, showing how AI can misrepresent cultural contexts.
Researchers propose a new way for AI to automatically gather and prepare its own specialized training data. This could make AI models better at niche tasks without human help. The approach, called 'Autonomous Agentic Data Engineering,' lets AI act as its own data engineer, potentially speeding up customization for fields like medicine or law.
Researchers have developed VFEAgent, an AI system that automates Finite Element Analysis (FEA) from images and text descriptions. This could make advanced engineering tools accessible to non-experts, speeding up design processes.
Scientists have created StoryMI, a multi-AI system that can generate realistic therapeutic dialogues. This tool could help train therapists and provide new ways to practice motivational interviewing techniques.
Researchers found that different large language models (LLMs) often categorize the same public comments in conflicting ways. This can shape what policymakers see, potentially biasing decisions. The study proposes a new audit pipeline to flag disagreements for human review.
Researchers created a new AI model called the Cognitive Categorical Transformer (CCT) that mimics how the human brain categorizes information. It outperforms a standard model by 12% on a language test, showing promise for smarter, more context-aware AI assistants.
Researchers found that the tone of your questions can change how well AI models like ChatGPT answer. Polite or neutral tones often get better results than aggressive or overly casual ones. This matters because it shows how small changes in how we talk to AI can make a big difference in the answers we get.
A new study tested AI-generated reviews for academic papers and found they don't always match human opinions. The research also reveals that authors can "game" the system by using AI to revise their papers before submission, raising serious questions about fairness and reliability in scientific publishing.
AI models can't reliably tell cause from effect, even with fine-tuning. Researchers prove this is a fundamental limitation and propose a new method to overcome it.
A new study reveals a simple method to bypass safety filters in AI image generators. The technique, called PAST2HARM, uses past tense prompts to trick models into creating harmful content.
AI models often verify facts better than they generate them, creating a 'factual gap'. This research explores why this happens and how it affects our trust in AI. New research reveals AI models often verify facts better than they generate them, creating a 'factual gap'. This research explores why this happens and how it affects our trust in AI.
Researchers have developed a new AI system that can detect human values in text, both explicit and implicit. This could help make AI decisions more aligned with ethical and moral considerations.
Researchers have introduced two advanced AI models designed for long-term coding tasks. These models, Laguna M.1 and XS.2, represent a significant leap in AI capabilities for software development.
Researchers developed ScientistOne, an AI system that conducts research autonomously while ensuring claims are verifiable. This could make AI-generated research more reliable for scientists and professionals.
Scientists have discovered that AI hallucinations are easier to detect in intermediate layers of AI models, not just the final output. They've developed a method to automatically find the best layers for spotting these errors, making AI more reliable.
Scientists argue that AI memory systems need to evolve beyond simple databases. Current approaches lead to issues like unchecked growth and forgotten information. Long-term AI agents need more sophisticated memory structures to function effectively.
Scientists are exploring whether AI models can solve real-world problems by repurposing objects in new ways. This research could lead to smarter robots and assistants that think more like humans.
A new study highlights how AI models can accidentally expose sensitive training data. This raises privacy concerns and challenges for AI developers. Researchers propose ways to mitigate these risks.
Researchers developed a way to make AI models reflect diverse cultural values more accurately. This could help AI understand and respect different cultural perspectives better.
Researchers created a benchmark to test AI's ability to model human beliefs and emotions. This could help build more empathetic and socially aware AI assistants.
Researchers developed POLAR, an AI system that helps robots learn personal preferences through long-term interactions. This could make future home robots more helpful by understanding individual needs.
Researchers have developed two AI systems that automate data collection and lecture analysis. These tools could make scientific work faster and more accessible.
Researchers created JobBench, a new way to test AI assistants on tasks that actually help people. It focuses on real-world work needs instead of just replacing jobs. This could lead to AI tools that empower workers rather than replace them.