CHAL: Advanced Multi-Agent Framework for AI Reasoning
Discover CHAL, a novel multi-agent framework enhancing AI reasoning with dynamic belief updates and ethical alignment for robust LLM debates.
DisaBench: Evaluating Disability Harms in AI Language Models
Discover DisaBench, a new framework assessing disability harms in AI language models with inclusive, participatory evaluation methods.
First-Order Progression: Size, Complexity & Decidability
Explore the size, complexity, and decidability of first-order progression in AI, enabling efficient reasoning about actions in dynamic knowledge bases.
Transferable User Preferences for Human-Aligned AI Decisions
Discover how CLIPR learns transferable user preferences to improve AI decision-making alignment with human values efficiently and effectively.
Interpretable Failure Modes in Vision-Language Models
Discover how REVELIO reveals interpretable failure modes in Vision-Language Models to improve safety in autonomous driving and robotics.