Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

[CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis

The Inter font family

SAM with text prompt

A diffuser implementation of Zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV23)

A markup-based typesetting system that is powerful and easy to learn.

a thin wrapper of chatgpt for improving paper writing.

[CVPR 2023] vMAP: Vectorised Object Mapping for Neural Field SLAM

A collection of reference environments for offline reinforcement learning

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

ReorientBot: Learning Object Reorientation for Specific-Posed Placement, ICRA 2022

SafePicking: Learning Safe Object Extraction via Object-Level Mapping, ICRA 2022

Moving to https://tangled.org/cduck.me/drawsvg/ Programmatically generate SVG (vector) images, animations, and interactive Jupyter widgets

Replacement icons for popular apps in the style of macOS Big Sur

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

PyTorch Implementation of MAML (Model-Agnostic Meta-Learning algorithm)

A Python toolkit used to train reinforcement learning algorithms against arcade games

MetaPost + TeX rendition of Oliver Byrne's "The first six books of the Elements of Euclid"

The modern video player for macOS.

Allows the use of video wallpaper and lock screen.

Summaries and notes on Deep Learning research papers

Distributed Deep learning with Keras & Spark

Typefaces for source code beautification

Local Fisher Discriminant Analysis in R