TMCnet

Breaking the 100M Token Limit: EverMind's MSA Architecture Achieves Efficient End-to-End Long-Term Memory for LLMs

This approach can be viewed as a memory plug-in for large models, providing a fresh perspective and direction for solving the ...
IEEE

OT-PFCNet: A Generative Pre-Alignment Framework for Cross-Domain Remote Sensing Retrieval

Abstract: This study addresses the feature representation gap in SAR-optical cross-modal retrieval caused by differences in data distributions and imaging mechanisms. Traditional approaches ...
IEEE

Multi-Agent Cooperative Exploration via Weighted Conditional Mutual Information in Sparse Reward Tasks

Abstract: Multi-agent Reinforcement Learning (MARL) algorithms have shown remarkable success in tasks requiring cooperation. However, in sparse reward scenarios, traditional MARL algorithms struggle ...