working-memory

We introduce temporal working memory (TWM), which aims to enhance the temporal modeling capabilities of Multimodal foundation models (MFMs). This plug-and-play module can be easily integrated into existing MFMs. With our TWM, nine state-of-the-art models exhibit significant performance improvements across QA, captioning, and retrieval tasks.

A curated list of apps, tools, and resources designed for ADHD brains — not adapted from neurotypical productivity systems. Most productivity tools assume you can plan ahead, maintain routines, and remember what you were doing five minutes ago. These don't.

Working memory tests on JavaScript (digit span, operation span, visual array, spatial span)

A simple Android app that helps you improve your working memory

N-Back Task Games designed to improve working memory and cognitive abilities.

Open source collection of cognitive training games (Dual N-Back, Stroop Test, Schulte Table) built with Next.js 15. Improve focus, memory, and attention.

Agent memory for LLM agents: 7 neuroscience-inspired layers (working, episodic, semantic, procedural) with FSRS spaced repetition and memory consolidation. Zero-dependency TypeScript library, Model Context Protocol (MCP) server, Vercel AI SDK middleware. Wins 9/9 answer-quality comparisons on LongMemEval-500 (3 judges, Bonferroni).

Personalized Training for the Sequence Learning task with the NAO robot and the MUSE EEG sensor

Spiking neuronal network simulations (Python, NEST Simulator) for continuous attractor working memory networks with short-term plasticity.

Example code accompanying the sternberg concept cell data release for Kyzar et al. (2024)

The classic dual n-back task implemented in Matlab; includes position, sound, and color options.

MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.

A setup to evaluate working memory using EEG signals

Estimate the demand of working memory in Social Cognition Tasks using HCP-fMRI dataset

Code for "Interpersonal movement synchrony responds to high- and low-level conversational constraints" (Paxton & Dale, 2017, Frontiers in Psychology).

Visual Working Memory Game in Python which gives you the gameplay data

Implementation of the change detection task aimed at measuring working memory capacity

A flutter app that can generate Chinese lyrics, poems and prose based on your given words and photos using GPT-2 and Working Memory Model. Designed to polish your twitter or moments.

This is our Neuromatch Academy 2020 computational neuroscience summer school group project.