github repository for Soft Q-based Diffusion Finetuning (SQDF)

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Standard Open Arm 100

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

DEAS + Isaac-GR00T + RoboCasa

Simulation benchmarks of GR1 Tabletop Tasks for GR00T N1

An open source implementation of CLIP.

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

The best ChatGPT that $100 can buy.

Latest Advances on Vison-Language-Action Models.

Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"

Recipes to train reward model for RLHF.

Large Concept Models: Language modeling in a sentence representation space

Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple regression tasks.

A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick

Process Reward Models That Think

Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

Unified Implementations of Offline Reinforcement Learning Algorithms

Official code repository for the paper Molecule Generation with Fragment Retrieval Augmentation (NeurIPS 2024)

Genetic-guided GFlowNets for Sample Efficient Molecular Optimization (NeurIPS 2024)

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model

The collection of awesome papers on alignment of diffusion models.

Official implementation for Diffusion Alignment as Sampling (DAS), ICLR'25, Spotlight

Derivative-Free, Training-Free, Guidance in Diffusion Models

Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (+ images)

A curated list for awesome discrete diffusion models resources.