A list of public EMG datasets and their papers, with a focus on raw EMG signals.

A collection of projects showcasing RAG, agents, workflows, and other AI use cases

Training and evaluating encoding models to predict fMRI brain responses to naturalistic video stimuli

Diagnose the performance of your RAG🩺

🦛 CHONK docs with Chonkie ✨ — The no-nonsense RAG library

AllTracker is a model for tracking all pixels in a video.

Project page of the paper "Learning general and distinctive 3D local deep descriptors for point cloud registration" published in IEEE T-PAMI

[ISPRS 2025] The official implementation of the paper CoFF "Cross-Modal Feature Fusion for Robust Point Cloud Registration with Ambiguous Geometry".

Leveraging Inlier Correspondences Proportion for Point Cloud Registration. https://arxiv.org/abs/2201.12094.

Containers for machine learning

Robust online multiband drift estimation in electrophysiology data

Neuronal recordings and Foundation models

Foundation neural network

notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references und…

Calibrated inference of spiking from calcium ΔF/F data using deep networks

Deepseek R1 zero tiny version own reproduce on two A100s.

AMEGA-LLM: Autonomous Medical Evaluation for Guideline Adherence of Large Language Models

Common clinical models in the forms of openEHR archetypes and GDL guidelines

Minimal reproduction of DeepSeek R1-Zero

The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices

Code repository for emg2pose dataset and model benchmarks

Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

first base model for full-duplex conversational audio

Learning Deep Learning

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A connectome-constrained deep mechanistic network (DMN) model of the fruit fly visual system in PyTorch.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling