About
Research & Development
Advancing Video Analysis: A New Approach to Moving Target Detection and Background Recovery
TLDR: This paper introduces uQRPCA+, a novel method for efficiently detecting moving targets and recovering backgrounds in color videos. It uses a fast quaternion-based...
Research & Development
Human Movement in Crisis: Predicting Mobility During Disasters with AI
TLDR: DisasterMobLLM is a new AI framework that uses Large Language Models (LLMs) and cross-city data to predict how people move during natural disasters....
Research & Development
Ethical Foundations for AI Code Generation
TLDR: A new research paper introduces Ethically Sourced Code Generation (ES-CodeGen), defining 11 critical dimensions for responsible AI code development, from data collection to...
Research & Development
UloRL: Boosting LLM Reasoning with Efficient Ultra-Long Output Training
TLDR: UloRL is a new reinforcement learning approach designed to improve the reasoning abilities of Large Language Models (LLMs) by efficiently handling ultra-long output...
Research & Development
AI-Powered Structural Drawings: From Language to AutoCAD
TLDR: This paper introduces a novel method using Large Language Model (LLM) agents to automatically generate structural drawings in AutoCAD from natural language descriptions....
Research & Development
Optimizing LLM Memory: HCAttention’s Approach to Extreme KV Cache Compression
TLDR: HCAttention is a new framework that drastically reduces the memory needed for Large Language Models (LLMs) to process long texts. It achieves this...