ReMe

A personalized cognitive training framework that aids in the rehabilitation of patients with cognitive impairments.

PremiumNewProductOthersCognitive TrainingMultimodal Large Models

ReMe is a personalized cognitive training framework jointly developed by Microsoft Research Asia and the Shanghai Mental Health Center, designed to provide personalized cognitive training for patients with cognitive impairments. This framework is based on Microsoft Azure's OpenAI services, utilizing multimodal large model technology to provide users with cognitive training experiences through various input and output modes, including text, images, and voice, in the form of a conversational agent. The innovation of ReMe lies in its ability to provide personalized and multimodal interaction capabilities, offering tailored training programs based on users' memory content and cognitive levels, thereby enhancing the relevance and effectiveness of training.

Product Finder

Product Submit

AI Models Finder

MCP Servers

MCP Client

MCP Inspector

Case Tutorials

Latest AI News

AI Daily Brief

ReMe

ReMe Visit Over Time

ReMe Visit Trend

ReMe Visit Geography

ReMe Traffic Sources

ReMe Alternatives

ReMe — A personalized cognitive training framework that aids in the rehabilitation of patients with cognitive impairments.

MM1.5 — Optimization and analysis of multimodal large language models

Large World Models — Large World Models: Understanding Video and Language

Multimodal-Maestro — More effectively prompt large multimodal models to unlock their potential.

DCLM — Comprehensive framework for building and training large language models

CuMo — An advanced architecture for extending multimodal large language models (LLMs).

lmms-finetune — A unified codebase for fine-tuning large multimodal models.

Entry Point AI — A platform for training customized large language models

Zhipu AI Large Model Open Platform — Integrate large models with just a few lines of code.

EAGLE — Exploration of the design space for multimodal large language models

Zidon TaiChu — A multimodal large model with stronger cognitive, comprehension, and creative capabilities.

Doubao Large Model — A large model developed by ByteDance, providing multimodal capabilities.

LongLLaVA — Efficiently extending multimodal large language models to 1,000 images.

Apollo-LMMs — Exploration of Video Understanding in Large Multimodal Models

Models Table — A comprehensive list and information about large language models

olmo-mix-1124 — Large-scale multimodal pre-training dataset

Auribus — The world's first open auditory training platform

InternVL2_5-38B — Advanced Multimodal Large Language Model Series

Comigo - Your Cognitive AI for ADHD — Provides cognitive AI support for individuals with ADHD to navigate a distracting world.

Pixtral-Large-Instruct-2411 — A 124B-parameter multimodal large language model.

AIM — Pre-training of Large-Scale Autoregressive Image Models

NVLM-D-72B — State-of-the-art multimodal large language model

MNN Large Model Android App — A fully functional Android app supporting multimodal capabilities with a large language model.

InternVL2_5-78B-MPO — This is an advanced series of multimodal large language models that demonstrate outstanding overall performance.

MyTrainingPlan — Personalized Marathon Training Plans

FP6-LLM — Efficiently serving large language models

SlowFast-LLaVA — A large language model for video understanding and reasoning that does not require training.

mPLUG-DocOwl — A modular multimodal large language model for document understanding

DocLLM — Multimodal Document Understanding Model