Native Multimodal Models are World Learners

Official implementation of "OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes".

Official repository for "AM-RADIO: Reduce All Domains Into One"

Official code of RDT 2

About Official repo of paper "SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models". A post-training framework that creates a cost-effective, self-iterative optimization loop.

Math-VR Benchmark & CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

[SIGGRAPH Asia 2025] OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion

Reference PyTorch implementation and models for DINOv3

Official Implementation of "UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation"

Implementation of "Hyperspherical Latents Improve Continuous-Token Autoregressive"

DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

Lumos Project: Frontier video unified model research by Alibaba DAMO Academy.

[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

🧑‍🚀 全世界最好的LLM资料总结（语音视频生成、Agent、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)

GPT chat with emotional expressions.

[ICLR 2025 Oral] Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling

A very simple GRPO implement for reproducing r1-like LLM thinking.

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Official PyTorch implementation of One-Minute Video Generation with Test-Time Training

Official implementation of the paper: "StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling"

[ICCV 2025] Official implementation of the paper "DreamCube: 3D Panorama Generation via Multi-plane Synchronization".