# apple-aiml-research/ml-halo

> Code for the HALO paper: a pipeline that generates synthetic data, trains a motion generator and a G1 humanoid tracking policy, and deploys them in simulation or on the real robot. It targets robotics researchers working on perceptive humanoid locomotion.

- Magnitude: 4.2 out of 10 — Early signal
- Stars: 303 total · +17 stars measured 2026-11-10, 00:26–06:04 UTC, ≈ 60 by evening
- Star trust: star growth looks organic
- Category: Hardware, IoT & robotics · Language: Python · Created: 2026-11-05 · Last push: 2026-11-05
- GitHub: https://github.com/apple-aiml-research/ml-halo · Homepage: https://apple-aiml-research.github.io/ml-halo/ · Page: https://gitnova.dev/en/r/apple-aiml-research/ml-halo

## Useful for

- Generate synthetic training data with Infinigen scenes and Isaac/MuJoCo rendering
- Train the G1 motion-tracking policy in Isaac Lab across three phases
- Run closed-loop control in MuJoCo or on the real G1 robot

## Why it’s here

- Star-counter measurements on 2026-11-10 (UTC), 00:26–06:04: 286 → 303 stars (+17). This is the change over that interval.
- Estimated end-of-day forecast: about +60 stars, using observed gains and the previous day.
- The repository is 5 days old and already has 303 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Recent forks include notable developers: @OlivierLaflamme (763 followers).

## 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: 24
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 57 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2

## Stars per day, last 6 days (oldest → newest, today is partial)

2026-11-05 … 2026-11-10: 93, 40, 27, 68, 55, 17

## Magnitude by day, last 5 days

11-06 5.0, 11-07 4.6, 11-08 3.7, 11-09 5.0, 11-10 4.2

## Similar by description

1. **google-deepmind/mujoco** — 7.5 · Breakout · Science & research · C++ · +133 stars measured 2026-11-10, 00:26–06:03 UTC, ≈ 465 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
2. **fuyichen0725/blinkmimic** — 1.3 · Cooling · Hardware, IoT & robotics · Python · +2 stars measured 2026-11-10, 00:32–06:10 UTC, ≈ 8 by evening
   BlinkMimic trains a single whole-body motion-tracking policy for the Unitree G1 across all 40 LAFAN1 clips in about 3 minutes on one RTX 4090, using a differentiable world model and mjlab/MuJoCo Warp.
   Full card: https://gitnova.dev/en/r/fuyichen0725/blinkmimic.md
3. **miao-org/awesome-supermimic** — 0.0 · Quiet · Learning & lists · Not enough measurements today
   A curated list of implementations, extensions and demos of SuperMimic, a method for humanoid whole-body control via a differentiable world model. It serves as an entry point for reproducing and adapting the method.
   Full card: https://gitnova.dev/en/r/miao-org/awesome-supermimic.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 2026-11-10 06:13 UTC, updated every 30 minutes.