Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first work to systematically explore R1 for video]

A curated list of Awesome Personalized Large Multimodal Models resources

CUDA Python: Performance meets Productivity

Code for "How far can we go with ImageNet for Text-to-Image generation?" paper

DataComp for Language Models

Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

GenEval: An object-focused framework for evaluating text-to-image alignment

A Unified Tokenizer for Visual Generation and Understanding

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation

[ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

A suite of image and video neural tokenizers

High-performance Image Tokenizers for VAR and AR

SEED-Voken: A Series of Powerful Visual Tokenizers

[ICLR 2025][arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization

SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer

[CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"

Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).

[CVPR'25] Official PyTorch implementation of Lumos: Learning Visual Generative Priors without Text

[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".

This repo contains evaluation code for the paper "AV-Odyssey: Can Your Multimodal LLMs Really Understand Audio-Visual Information?"

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

📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.

[ICLR 2025] Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.