# jwang771/3d-world-simulator

> Research project on 3D world simulation: a hybrid particle-voxel autoencoder plus a latent dynamics model for robotics tasks (cloth, rope, plug insertion, etc.). Python training code; data and checkpoints are promised later.

- Magnitude: 4.6 out of 10 — Early signal
- Stars: 167 total · +3 stars measured 2026-11-04, 09:50–10:39 UTC, ≈ 28 by evening
- Star trust: star growth looks organic
- Category: Science & research · Language: Python · Created: 2026-11-02 · Last push: 2026-11-02
- GitHub: https://github.com/jwang771/3d-world-simulator · Page: https://gitnova.dev/en/r/jwang771/3d-world-simulator

## Useful for

- Train the VAE for a specific robotics task via scripts/train_vae.py
- Precompute dataset latents with export_latents.py to speed up dynamics training
- Train the latent dynamics model with an autoregressive schedule via train_dynamics.py

## Why it’s here

- Star-counter measurements on 2026-11-04 (UTC), 09:50–10:39: 164 → 167 stars (+3). This is the change over that interval.
- Estimated end-of-day forecast: about +28 stars, using observed gains and the previous day.
- The repository is 2 days old and already has 167 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #191.
- About 12 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 14
- Issues and pull requests: 2
- Watchers: 3
- Average over the last week: 62 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 4

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-11-02 … 2026-11-04: 83, 77, 3

## Spotted in now

- Top new repositories this week: #191

## More in this category

1. **RikiyaT/lm_understand-logs** — 6.7 · Early signal · Science & research · Python · +105 stars measured 2026-11-04, 00:17–10:38 UTC, ≈ 276 by evening
   Complete logs of every experiment from the blog post 'LLMs can understand and write neural network weights', including prompts, model replies, sandboxed code runs, evaluations and the networks read or written.
   Full card: https://gitnova.dev/en/r/RikiyaT/lm_understand-logs.md
2. **kornia/kornia** — 4.3 · Peaking · Science & research · Python · +10 stars measured 2026-11-04, 00:17–10:39 UTC, ≈ 40 by evening
   Kornia is a differentiable computer vision and geometry library built on PyTorch: over 1,200 GPU-accelerated operators for image processing, feature detection/matching, minimal solvers and camera models, all keeping gradients. It is aimed…
   Full card: https://gitnova.dev/en/r/kornia/kornia.md
3. **Yuan1z0825/nature-skills** — 3.1 · Steady · Science & research · Python · +101 stars measured 2026-11-04, 00:21–10:41 UTC, ≈ 205 by evening
   A collection of reusable SKILL.md skills for AI agents that help researchers: reading and translating papers, academic polishing, generating figures, and preparing Nature-style presentations.
   Full card: https://gitnova.dev/en/r/Yuan1z0825/nature-skills.md
4. **openai/math** — 2.4 · Cooling · Science & research · Lean · +14 stars measured 2026-11-04, 00:22–10:44 UTC, ≈ 33 by evening
   A collection of mathematical manuscripts and Lean formalizations produced by an internal OpenAI model while solving open research problems. Intended for mathematicians and researchers studying the results and verifying proofs.
   Full card: https://gitnova.dev/en/r/openai/math.md
5. **google-deepmind/mujoco** — 1.8 · Steady · Science & research · C++ · +5 stars measured 2026-11-04, 00:25–10:46 UTC, ≈ 13 by evening
   A general-purpose physics engine for simulating articulated structures with contacts, used in robotics, biomechanics, graphics and reinforcement learning. Provides a C API, Python bindings, a native GUI and a Unity plug-in.
   Full card: https://gitnova.dev/en/r/google-deepmind/mujoco.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-04 10:53 UTC, updated every 30 minutes.