About
Research & Development
CREW-WILDFIRE: A New Benchmark for Scaling Multi-Agent AI in Complex Wildfire Scenarios
TLDR: CREW-WILDFIRE is a new open-source benchmark designed to evaluate the scalability, robustness, and coordination of LLM-based multi-agent AI systems in complex, dynamic, and...
Research & Development
Community-Driven AI: A Framework for Contestability and Value Pluralism
TLDR: The paper introduces "Community-Defined AI Value Pluralism" (CDAVP), a socio-technical framework that empowers diverse, self-organizing communities to define and apply their own values...
Research & Development
Advancing AI in 2048: New Reinforcement Learning Approaches for Delayed Rewards
TLDR: This research introduces Horizon-DQN (H-DQN) and adapts Quantile Regression DQN (QR-DQN) to tackle the challenge of delayed and sparse rewards in reinforcement learning,...
Research & Development
Boosting Reinforcement Learning Efficiency with Uncertainty-Guided Exploration
TLDR: A new research paper introduces FBEE Q, an epistemically-guided exploration framework for zero-shot Reinforcement Learning. By actively minimizing the uncertainty of its learned...
Research & Development
Unlocking AI’s Logic: A New Approach for Discovering Interpretable Scientific Models
TLDR: Ex-HiDeNN is a novel AI framework that combines deep learning (C-HiDeNN-TD) with symbolic regression (PySR) to automatically discover accurate and human-understandable mathematical equations...
Research & Development
Enhancing Graph Learning with External Knowledge and Latent Space Constraints
TLDR: Latent Space Constrained Graph Neural Networks (LSC-GNN) is a novel framework designed to improve the robustness and performance of Graph Neural Networks (GNNs)...