Generative Models by Stability AI

The open-source code for the NeurIPS 2025 paper, "Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning."

[Nature Machine Intelligence 2025] Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception

Official code of paper "DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution"

verl: Volcano Engine Reinforcement Learning for LLMs

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

[NeurIPS 2025] LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

The code repository of UniRL

[NeurIPS 2025] MMaDA - Open-Sourced Multimodal Large Diffusion Language Models

SC-Depth (V1, V2, and V3) for Unsupervised Monocular Depth Estimation Webpage:https://jiawangbian.github.io/sc_depth_pl/

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Dense Prediction Transformers

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

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

CODA: Repurposing Continuous VAEs for Discrete Tokenization

A curated list of recent diffusion models for video generation, editing, and various other applications.

Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

LaTeX Thesis Template for Tsinghua University

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

Official implementation of “4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models” (CVPR 2025)

DUSt3R: Geometric 3D Vision Made Easy

[CVPR 2025] Official repo for ART:Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

Official inference repo for FLUX.1 models

[TPAMI 2023] SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention

Official implementation of Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion