Rethinking One-Step Image Editing through ChordEdit: Reproduction, Simplification, and New Insights

DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images

[CVPR 2026 Best Paper Finalist] Pixel Diffusion Transformers for Image Generation

Code repo for EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

GenClaw: Code-Driven Agentic Image Generation

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

Awesome Audio-Visual Intelligence, Survey of Audio-Visual Intelligence

SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

[CVPR 2026] WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories (WorldExpand of HY-World 2.0)

[CVPR 2026] Official code of the paper "Meta-CoT: Enhancing Granularity and Generalization in Image Editing"

Project Lyra: Open Generative 3D World Models

HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

FrameCrafter: Novel View Synthesis as Video Completion

Information collection for the Happy Horse AI video generator model. Official demo and updates at happyhorses.io.

[CVPR2026] VOSR: A Vision-Only Generative Model for Image Super-Resolution

[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

Official Implementation for paper "Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm"

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

Our method reconstructs 3D worlds from video diffusion models using non-rigid alignment to resolve inherent 3D inconsistencies in the generated sequences.

[CVPR 2026] DROID-SLAM in the Wild

CheXOne: A Reasoning-Enabled Vision–Language Foundation Model for Chest X-ray Interpretation