Stars
Code for the EMNLP2025 paper "Joint Modeling of Entities and Discourse Relations for Coherence Assessment".
verl: Volcano Engine Reinforcement Learning for LLMs
Native Multimodal Models are World Learners
[CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
Implementation of MagViT2 Tokenizer in Pytorch
SEED-Voken: A Series of Powerful Visual Tokenizers
"Deep Generative Modeling": Introductory Examples
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models
TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation
Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
Mechanistic Interpretability Visualizations using React
experiments on the use of linear classifier heads for llm-as-a-judge tasks.
A Survey on Multimodal Retrieval-Augmented Generation
A library for mechanistic interpretability of GPT-style language models
Code for the ACL2025 paper "Discourse Relation-Enhanced Neural Coherence Modeling".
[NeurIPS 2024] How do Large Language Models Handle Multilingualism?
This repository contains the data and the code for the paper "Control Illusion: The Failure of Instruction Hierarchies in Large Language Models"
An updated version of William Hamilton's histwords code (https://github.com/williamleif/histwords
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)