About
Research & Development
Unified AI System Tackles Challenging Delivery and Inspection Routes
TLDR: A new deep reinforcement learning framework, UD3RL, has been developed to solve the Close-Enough Traveling Salesman Problem (CETSP). Unlike traditional methods, UD3RL uses...
Research & Development
Unlocking Neural Timing: A Quantum-Inspired Leap in Action Potential Prediction
TLDR: This research introduces a Quantum-Inspired Leaky Integrate-and-Fire (QI-LIF) model for predicting action potential (AP) onset timing. Unlike traditional models that struggle with accuracy,...
Research & Development
Decoding Spatial Intelligence in Large Multimodal Models
TLDR: A new research paper introduces 'multimodal function vectors' (FVs) extracted from specific attention heads in Large Multimodal Models (LMMs) like OpenFlamingo-4B. These FVs...
Research & Development
AI Agents Accelerate New Alloy Development for 3D Printing
TLDR: A new multi-agent AI system, leveraging Large Language Models (LLMs) and the Model Context Protocol (MCP), automates and accelerates the discovery of new...
Research & Development
Enhancing Electric Vehicle Safety and Grid Integration with Multimodal AI Alerts
TLDR: A new research framework utilizes multimodal large language models (LLMs) to improve the safety and interpretability of electric vehicles (EVs) within smart grids....
Research & Development
Unmasking AI Vulnerabilities: A New Approach to Multimodal Safety Testing
TLDR: ARMS is an adaptive AI agent designed to systematically test the safety of vision-language models (VLMs) by automatically generating diverse and effective attacks....