9 articles
A new AI framework boosts LLM accuracy by 70% and cuts token usage by 39% through smarter reasoning allocation.
AutoGEO framework by CMU researchers optimizes web content for AI search engines, boosting visibility with dual LLM models.
A multi-agent AI system that automates CUDA GPU programming now hits near-100% success on complex optimization tasks.
A novel automated translation framework using test-time compute scaling has demonstrated markedly higher quality output, with LLM judges preferring its translations four times more often than standard approaches.
A breakthrough training method called Co-rewarding helps AI language models think better and learn more reliably without needing human-verified answers, showing real improvements on mathematical problem-solving tests.
Researchers released a lightweight open-source AI agent framework that compresses complex agent architecture into a compact Python system.
University of Alberta researchers developed Reason2Decide, a training framework that makes AI medical predictions more explainable using models 40 times smaller than GPT-4.
Researchers built a new system that lets AI follow tasks one step at a time - watching how objects physically change, instead of merely tagging what action happens.
A new framework helps AI builders choose among three options - long context models, retrieval augmented generation and agentic systems. The goal is to fix AI deployments that run slowly or waste resources.
We use cookies to improve your experience on our site and to show you relevant advertising. To find our more, read our privacy policy and cookie policy
Peter Smith
Eseandre Mordi
Marina Lyubimova
Saad Ullah
