ai development
6 notes, newest first.
From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence
The paper discusses the development of artificial intelligence that can act in the physical world. It highlights the importance of World Action Models (WAMs) and identifies three gaps in current research: model roles…
Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination
Researchers have developed a new framework called G-Frame that helps lightweight Large Language Models perform better in rule-based scientific domains by reducing hallucinations. They created a new model called…
World Wide Models: Literary Tools for Cultural AI
The paper suggests that large language models (LLMs) are shaping a new form of cultural encounter, and proposes a framework for developing more nuanced textual models in AI that draw on literary disciplines such as…
World Wide Models: Literary Tools for Cultural AI
The paper proposes a framework for developing culturally literate AI by integrating literary tools such as comparative reading, narratology, critical theory, world literature, and translation. It emphasizes the…
World Wide Models: Literary Tools for Cultural AI
The paper discusses the use of literary analysis tools for developing culturally literate AI, focusing on the challenges posed by massive automated monolingual encounters.
AutoMem: Automated Learning of Memory as a Cognitive Skill
Researchers developed AutoMem, a framework to automate the learning of memory as a cognitive skill for large language models (LLMs). This improves the performance of LLMs significantly in long-horizon games by treating…
