# roboterax/video-prediction-policy-2

> Official implementation of Video Prediction Policy 2, a world-action model that couples event-level video pretraining with a single-step visual planner and an action module for robot manipulation.

- Magnitude: 4.2 out of 10 — Early signal
- Stars: 106 total · +25 stars measured 2026-10-09, 09:19–13:10 UTC, ≈ 49 by evening
- Star trust: star growth looks organic
- Category: Hardware, IoT & robotics · Language: Python · Created: 2026-10-08 · Last push: 2026-10-09
- GitHub: https://github.com/roboterax/video-prediction-policy-2 · Homepage: https://robert-gyj.github.io/video-prediction-policy-2/ · Page: https://gitnova.dev/en/r/roboterax/video-prediction-policy-2

## Useful for

- Reproduce VPP2 results on the RoboDojo closed-loop evaluation benchmark
- Fine-tune the LIBERO policy checkpoint and test generalization on LIBERO-OOD/PRO
- Train a video-action policy from downloadable Hugging Face or ModelScope checkpoints

## Why it’s here

- Star-counter measurements on 2026-10-09 (UTC), 09:19–13:10: 81 → 106 stars (+25). This is the change over that interval.
- Estimated end-of-day forecast: about +49 stars, using observed gains and the previous day.
- The repository is 1 day old and already has 106 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #162.

## 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: 2
- Issues and pull requests: 1
- Watchers: 1
- Average over the last week: 57 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 6

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

2026-10-04 … 2026-10-09: 0, 0, 0, 0, 66, 25

## Spotted in now

- Top new repositories this week: #162

## Similar by description

1. **black-forest-labs/flux-action** — 1.6 · Steady · Hardware, IoT & robotics · Python · +6 stars measured 2026-10-09, 00:13–13:18 UTC, ≈ 10 by evening
   Full fine-tuning and action prediction toolkit for FLUX 3 Action: data preparation, distributed training, checkpointing, export and inference for DROID and SO-101 robotics tasks.
   Full card: https://gitnova.dev/en/r/black-forest-labs/flux-action.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 2026-10-09 13:25 UTC, updated every 30 minutes.