Stars
This is a list of relevant papers for 3D Geometric Foundation Models and Applications.
Kimi Code CLI — The Starting Point for Next-Gen Agents
Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh R…
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
[NeurIPS 2025] ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction
Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds. 面向游戏与虚拟世界的AI原生渲染引擎
Code of Strips as Tokens: Artist Mesh Generation with Native UV Segmentation. ACM Transactions on Graphics (SIGGRAPH 2026)
CrossGen: Learning and Generating Cross Fields for Quad Meshing
OctFormer: Octree-based Transformers for 3D Point Clouds [SIGGRAPH 2023]
[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)
A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。
🔬 Harness Vibe Research with Self-evolving AI Scientists
[ICML'26] Official repository of Utonia: Toward One Encoder for All Point Clouds
😼 优雅地使用基于 clash/mihomo 的代理环境
[ICLR 2026] PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data
MATStruct: High-Quality Medial Mesh Computation via Structure-aware Variational Optimization (SIGGRAPH Asia 2025)
[CVPR 2026] FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
PyTorch implementation of Neural Dual Contouring.
Reference implementation for DPO (Direct Preference Optimization)
Official Implementation of "Splat the Net: Radiance Fields with Splattable Neural Primitives"
Code release for CVPR 2025 paper "Textured Gaussians for Enhanced 3D Scene Appearance Modeling".
[3DV 2026] FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
Official code of paper: MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.