friedeggs

CounterfactualWorldModels

An approach to building pure vision foundation models by prompting masked predictors with "counterfactual" visual inputs.

LlamaGym

Fine-tune LLM agents with online reinforcement learning

nerfies.github.io

svox2

Plenoxels: Radiance Fields without Neural Networks

neural_renderer

A PyTorch port of the Neural 3D Mesh Renderer

unsup3d

(CVPR'20 Oral) Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild

pyrender

Easy-to-use glTF 2.0-compliant OpenGL renderer for visualization of 3D scenes.

redner

Differentiable rendering without approximation.

social-mdp-framework

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

colmap

COLMAP - Structure-from-Motion and Multi-View Stereo

kaolin

A PyTorch Library for Accelerating 3D Deep Learning Research

mental_img_recon

Mental image reconstruction from human brain activity

thompson

Thompson Sampling Tutorial

font8x8

8x8 monochrome bitmap fonts for rendering

three.js

JavaScript 3D Library.

loco-mujoco

Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

dit

Python package for information theory.

gpmf-parser

Parser for GPMF™ formatted telemetry data used within GoPro® cameras.

deepsvg

[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.

graphologue

Use LLM to stream diagrams, instead of tokens, in real-time! (UIST 2023 Paper)

ToRA

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

geosolver

Geometry Question Solver (GeoS)

codellama

Inference code for CodeLlama models

Category_Theory_Machine_Learning

List of papers studying machine learning through the lens of category theory

pdfThumbnails

A small script to generate thumbnail images for pdf files, based on pdf.js

msdm

Models of Sequential Decision-Making

coauthor-interface

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

aither

Collaborate with friends in real-time on an AI-enabled desktop in the browser