This is a list of relevant papers for 3D Geometric Foundation Models and Applications.

美股指南

SciPilot Skills family - Publication-grade scientific figure copilot for Claude Code

TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.

[CVPR 2026] [Best Paper Finalist] [Oral] Official repository of Vision Test-Time Training

News: the 10k dataset is ready for download.

MiMo Code: Where Models and Agents Co-Evolve

Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"

Latent Spatial Memory for Video World Models

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

The first "ImageNet" 3D dataset.

Muon is an optimizer for hidden layers in neural networks

[CVPR 2026 Oral] Official implementation for ChordEdit: One-Step Low-Energy Transport for Image Editing

Simple 3d mapping and physic simulation on blender

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

high-performance inference and serving library for interactive autoregressive video and world models

Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation

Official implementation of R^3: 3D Reconstruction via Relative Regression.

Visualize, query, and stream to train on multimodal robotics data.

GLUEMAP: Global Structure-from-Motion Meets Feedforward Reconstruction

Muon is Scalable for LLM Training

Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction

A Minimalist, Batteries-included Repository for Advancing World Model Science.

[ICML 2026] iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning

HorizonStream Official Implementation

Official AI skills for GSAP. These skills teach AI coding agents how to correctly use GSAP (GreenSock Animation Platform), including best practices, common animation patterns, and plugin usage.

[ICLR26] Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling