Incentivizing "Thinking with Long Videos" via Native Tool Calling

MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.

MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.

MiroRL is an MCP-first reinforcement learning framework for deep research agent.

MiroThinker is a series of open-source agentic models trained for deep research and complex tool use scenarios.

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

🏠 [ICCV 2025] MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

Memory-Guided Diffusion for Expressive Talking Video Generation

Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

Give us minutes, we give back a faster Mamba. The official implementation of "Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training".

AnchorAttention: Improved attention for LLMs long-context training

(ICLR 2025 spotlight) "Poison-splat: Computation Cost Attack on 3D Gaussian Splatting"

[ECCV'24] Kalman-Inspired Feature Propagation for Video Face Super-Resolution

Official Code for ECCV 2024 paper — One-Shot Diffusion Mimicker for Handwritten Text Generation

💬 An extensive collection of exceptional resources dedicated to the captivating world of talking face synthesis! ⭐ If you find this repo useful, please give it a star! 🤩

Code release for the ECCV 2024 paper 'Fully Test-Time Adaptation for Monocular 3D Object Detection'

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

A Next-Generation Training Engine Built for Ultra-Large MoE Models

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

Consistency Distilled Diff VAE

Generative Models by Stability AI

[ICCV2023] Dataset Quantization

Refine high-quality datasets and visual AI models

Official repo for consistency models.

This repository is the official implementation of Disentangling Writer and Character Styles for Handwriting Generation (CVPR 2023)

Image to prompt with BLIP and CLIP