A feed-forward 3D foundation model for reconstructing scenes from streaming data

Compile agent conversations!

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

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

将 B 站视频转化为结构化的 Markdown 阅读笔记 —— 看视频太慢，不如读笔记。

Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D

[NeurIPS 2025] HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis

[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

Helios: Real Real-Time Long Video Generation Model

[CVPR 2026] Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".

Official repository of Utonia: Toward One Encoder for All Point Clouds

Scalable View Synthesis Model [CVPR 2026]

[CVPR 2026 Highlight] Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.

Visual Causal Flow

Causal video-action world model for generalist robot control

Advancing Open-source World Models

Masked Depth Modeling for Spatial Perception

[CVPR 2026] Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

The official implementation of InfiniteVGGT

一个基于nano banana pro🍌的原生AI PPT生成应用，迈向真正的＂Vibe PPT＂; 支持上传任意模板图片；上传任意素材&智能解析；一句话/大纲/页面描述自动生成PPT；口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌

[CVPR 2026 Highlight] NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Sharp Monocular View Synthesis in Less Than a Second

Native and Compact Structured Latents for 3D Generation