Pixel-Space Generative Models

Unifying 3D Mesh Generation with Language Models

LLM inference in C/C++

OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]

Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

Code for D-DiT

ByteCheckpoint: An Unified Checkpointing Library for LFMs

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

This is the project repo for 'PSG-4D-LLM'.

Memory-optimized training library for diffusion models

verl: Volcano Engine Reinforcement Learning for LLMs

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Train transformer language models with reinforcement learning.

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

10 Lessons to Get Started Building AI Agents

[CVPR 2025] DreamRelation: Bridging Customization and Relation Generation

Official PyTorch implementation for "Large Language Diffusion Models"

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

Paper List of Inference/Test Time Scaling/Computing

(TPAMI 2024) A Survey on Open Vocabulary Learning

[T-PAMI-2024] Transformer-Based Visual Segmentation: A Survey

This is a repo to track the latest autoregressive visual generation papers.

Fast and memory-efficient exact attention

Implementation of [CVPR 2025] "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

CogView4, CogView3-Plus and CogView3(ECCV 2024)

A Unified Tokenizer for Visual Generation and Understanding

[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Open reproduction of MUSE for fast text2image generation.