About
Research & Development
Physics-Guided AI for Critical Industrial Applications
TLDR: PKG-DPO is a novel AI framework that integrates Physics Knowledge Graphs (PKGs) with Direct Preference Optimization (DPO) to create AI systems that provide...
Research & Development
Enhancing AI’s Judgment: Teaching Large Reasoning Models When to Abstain
TLDR: Large Reasoning Models (LRMs) often fail to abstain from unanswerable questions, generating incorrect answers or getting stuck, despite internally recognizing the problem. Researchers...
Research & Development
Boosting LLM Reasoning: A New Strategy for Dynamic Multi-Model Collaboration
TLDR: This paper introduces a novel approach called Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units (DDS). It enhances language model...
Research & Development
Enhancing Code Vulnerability Detection with Counterfactual Data Augmentation
TLDR: The VISION framework introduces a novel approach to robust and interpretable code vulnerability detection. It uses Large Language Models to generate "counterfactual" code...
Research & Development
Agents That Learn From Life: A New Framework for Continuous AI Growth
TLDR: The paper introduces Experience-driven Lifelong Learning (ELL), a framework for creating self-evolving AI agents that continuously learn and adapt through real-world interactions. It's...
Research & Development
Unlocking Math Question Difficulty: A New AI Approach Beyond Language Analysis
TLDR: A new AI model called APME uses reinforcement learning and a Multi-Armed Bandit framework to estimate math question difficulty. It analyzes solver performance...