About
Research & Development
Automating Photonic Circuit Design with AI Agents: Introducing PhIDO
TLDR: PhIDO is a new multi-agent AI framework that automates the design of Photonic Integrated Circuits (PICs) from natural language requests to layout mask...
Research & Development
Smart Parking: Predicting Availability Without Costly Sensors
TLDR: A new framework predicts parking availability using geospatial data and machine learning, eliminating the need for expensive sensors. It integrates street maps, mobility,...
Research & Development
Enhancing Teamwork in AI: A New Approach to Multi-Agent Reinforcement Learning
TLDR: Researchers have developed an enhanced multi-agent reinforcement learning algorithm, building upon the existing MADDPG framework. This new approach introduces a unique parameter that...
Research & Development
RynnEC: A Video Multimodal Model for Embodied Cognition
TLDR: RynnEC is a new video multimodal large language model (MLLM) designed for embodied cognition. It uses a region encoder and mask decoder for...
Research & Development
FINCH-ZK: Enhancing Factual Reliability in Large Language Models
TLDR: FINCH-ZK is a novel black-box framework designed to detect and mitigate hallucinations in Large Language Model (LLM) outputs without requiring external knowledge. It...
Research & Development
Beyond Rephrasing: LMTransplant’s Novel Approach to Text Data Augmentation
TLDR: LMTransplant is a new text data augmentation method that uses large language models (LLMs) to create highly diverse and creative content-level variants. Unlike...