Trending Repos
TrendingRisersNewestTopicsCollectionsCompare
TrendingRisersNewestTopicsCollectionsCompare
Trending Repos

Trending Repos tracks GitHub momentum from stars, forks, and rank history.

Explore

TrendingRisersNewestTopicsCollections

Tools

SearchCompareBadgesSubmit a repo

Project

AboutStatsDevelopersContactPrivacy
Back to trending
Physics-Scaling/GeoPT avatar

Physics-Scaling/GeoPT

GitHub

Official Code for "GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training" (ICML 2026) https://arxiv.org/pdf/2602.20399

Python190 stars23 forks
foundation-modelsphysics-simulationpretrainingself-supervised-learning

Momentum

Physics-Scaling/GeoPT has 190 GitHub stars.

It currently ranks #38918 daily, #39055 weekly, #40003 monthly by momentum on Trending Repos; its best-ever rank is #7654.

Rankings

PeriodRankScore
Daily
#389180.0
Weekly
#390550.0
Monthly
#400030.0
How scoring works

Engagement

Total stars
Daily new stars

Similar trending repositories

  • rasbt/LLMs-from-scratchImplement a ChatGPT-like LLM in PyTorch from scratch, step by stepJupyter Notebook108,216 stars#383 this week
  • OpenMOSS/MOSS-ImageOfficial repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.Python2,802 stars#742 this week
  • jrouwe/JoltPhysicsA multi core friendly rigid body physics and collision detection library. Written in C++. Suitable for games and VR applications. Used by Horizon Forbidden West and Death Stranding 2.C++12,270 stars#1374 this week
  • baidu-baige/LoongForgeA high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3 and more.Python837 stars#2450 this week
  • limix-ldm-ai/LimiXLimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2609.17488Python4,412 stars#4195 this week
  • Nixtla/nixtlaTimeGPT-2.1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.Jupyter Notebook4,045 stars

Embeds

Best rank #7654
Physics-Scaling/GeoPT badge
Markdown
#4960 this week