DeepSeek’s conditional memory fixes silent LLM waste: GPU cycles lost to static lookups

Through systematic experiments DeepSeek found the optimal balance between computation and memory with 75% of sparse model ...
IEEE

Flight Attendant Route Planning and Resource Allocation Algorithm Based on Reinforcement Learning and Dynamic Programming

Abstract: In this paper, flight attendants' route planning and resource allocation algorithms based on feedback learning (RL) and dynamic programming (DP) are studied. In the air transport industry, ...
IEEE

Distributed Observer-Based Dynamic-Memory Event-Triggered Security Control for Interconnected Linear Systems

Abstract: This paper explores the observer-based event-triggered security control problem for linear systems. Initially, a distributed dynamic-memory event-triggered scheme (DMETS) is proposed based ...