About
Research & Development
Advancing Personalized AI: Memory Mechanisms for Complex Reasoning
TLDR: This research introduces Multi-hop Personalized Reasoning (MPR) tasks for LLM-based agents, requiring multi-step reasoning over user-specific information. It evaluates explicit and implicit memory...
Research & Development
CardAIc-Agents: A Flexible AI Framework for Comprehensive Cardiac Support
TLDR: CardAIc-Agents is a novel multimodal AI framework designed to enhance cardiac care by overcoming limitations of existing AI. It features a CardiacRAG agent...
Research & Development
Advancing AI’s Ability to Generate Code from Charts with Multimodal Reinforcement Learning
TLDR: A new research paper introduces Multimodal Structured Reinforcement Learning (MSRL), a method that significantly improves AI's ability to generate code from visual charts....
Research & Development
Predicting Human Actions: How Knowledge Graphs Inform Robotic Assistance in Household Tasks
TLDR: This research explores using Knowledge Graphs (KGs) to predict human actions in household tasks for robotics. It investigates how Knowledge Graph Completion (KGC)...
Research & Development
CausalPlan: Enhancing LLM Agent Collaboration Through Causal Reasoning
TLDR: CausalPlan is a new framework that improves the collaboration of Large Language Model (LLM) agents by integrating explicit structural causal reasoning into their...
Research & Development
Learning from Logic: How Probabilistic Grammars Improve SMT Solver Performance
TLDR: Researchers introduce a new method called ProbGen for Satisfiability Modulo Theories (SMT) solvers, which tackles complex logic problems by dynamically learning from existing...