Repository profile

THUSI-Lab / GameScaling

Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.

  • embodied-agent
  • game-agent
  • game-ai
  • mihoyo
  • scaling-laws
  • tsinghua
  • vlm

Why this project

  • Positive net stars in 10 of 10 daily intervals.
  • 2 active contributors, 13 commits and 0 merged PRs in four complete weeks.
Recommendation evidence

sampled_snapshots · 2026-10-23T02:05:36.991196+00:00 to 2026-11-02T02:06:07.918766+00:00 · potential-v1

Showing the last complete activity period while new data is collected.

Discovery signals are not a prediction of quality or future success.

Repository overview

Public GitHub metrics and OpenPulse observations
GitHub stars459
Public forks24
Activity · 4 weeks
Steady activity49/100

Showing the last complete activity period while new data is collected.

Growth · 24h+4 stars
Growth · 7d+71 stars
Growth · 30d+441 stars

Repository activity

Four complete UTC weeks · 2026-09-27 to 2026-10-25
Commits13
Merged pull requests0
Active contributors2

Relative score across tracked public repositories with complete data. It describes recent activity, not project quality. Updated .

AI-attributed commits Pilot

Not yet analyzed · hot-project pilot

—

Share of checked commits with explicit AI attribution, not the share of AI-generated code.

View basis

Based on explicit public attribution in recent default-branch commits. Not the percentage of AI-generated code; unmarked use cannot be detected.

Star activity

Last 7 days
26 Oct8 observed days · gaps preserved02 Nov

Observed star growth

Samples or dated GitHub history
24h +4 stars Measured from observations 01 Nov 2026 → 02 Nov 2026
7d +71 stars Measured from observations 26 Oct 2026 → 02 Nov 2026
30d +441 stars GitHub history · as of 2026-10-29 10 Oct 2026 → 30 Oct 2026