About
Research & Development
Adaptive LLMs: A Fuzzy Logic Framework for Dynamic User Interaction
TLDR: A new prompting framework combines a natural language boundary prompt with a fuzzy scaffolding logic JSON schema to enable Large Language Models (LLMs)...
Research & Development
Beyond Vision: Language Models Reshape Remote Sensing Image Understanding
TLDR: This research paper proposes a paradigm shift in remote sensing image interpretation from a 'vision-centered' to a 'language-centered' approach, inspired by the Global...
Research & Development
Enhancing Multi-Agent Cooperation Through Adaptive Credit Assignment
TLDR: A new research paper introduces Multi-level Advantage Credit Assignment (MACA), a novel approach to cooperative multi-agent reinforcement learning. MACA addresses the complex challenge...
Research & Development
Advancing Severe Weather Prediction with a New AI Model and Dataset
TLDR: MeteorPred introduces a novel AI system for severe weather forecasting, comprising MP-Bench, the first large-scale temporal multimodal dataset with 421,363 pairs of meteorological...
Research & Development
Pushdown Reward Machines: Expanding RL’s Reach to Complex Behaviors
TLDR: Pushdown Reward Machines (pdRMs) are a new extension of Reward Machines for Reinforcement Learning (RL) that use a stack to recognize and reward...
Research & Development
Enhanced Local Search for Distributed Optimization: A New Framework for Multi-Agent Systems
TLDR: The research paper introduces Distributed Guided Local Search (DGLS), a novel algorithm for Distributed Constraint Optimization Problems (DCOPs). DGLS addresses the limitations of...