Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

aim-uofa/MARBLE

Multi-Aspect Reward Balance for Diffusion RL

Visit GitHub
Python
40
2 contributors
Apache License 2.0
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast aim-uofa/MARBLE is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

May 2026 – Oct 2026

Stars +40 in 6 months

02040
34

Forks +0 in 6 months

01

Merged PRs 0 in 6 months

01

Trendshift Trendingthe best rank each month, on any day it made the top 25

Not in the Trendshift top 25 in this period

May 2026Jun 2026Jul 2026Aug 2026Sep 2026Oct 2026
The left and right arrow keys step from month to month; Home and End go to the first and the last

Stars, forks, merged pull requests and best Trendshift Trending rank, by month
MonthStars gainedForks gainedMerged PRs
May 2026+34+00
June 2026+4+00
July 2026+1+00
August 2026+1+00
September 2026+0+00
October 2026+0+00
Total+40+00
  • 1#1 on the list
  • 7Best rank that month
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. May 221 post

    • Paper: Project: Code: Eliminates the specialist sample problem and gradient conflicts across PickScore, HPSv2, OCR, GenEval & Aesthetic rewards without manual stage scheduling.

      Read full on X, posted by @Dhiraj7kr

      @Dhiraj7kr · x.com

  2. May 211 post

    • Paper: Project: Code: Eliminates the specialist sample problem and gradient conflicts across PickScore, HPSv2, OCR, GenEval & Aesthetic rewards without manual stage scheduling.

      Read full on X, posted by @Dhiraj7kr

      @Dhiraj7kr · x.com

You might also like

Repositories close to aim-uofa/MARBLE
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

worldbench/DiffusionOPSD

Python

🔥 On-Policy Self-Distillation in Diffusion Models

9619

scxue/advantage_weighted_matching

Python

Official code for paper Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

1001

End2End-Diffusion/diffusion-bench

Python

Towards Holistic evaluation of Generative Diffusion Transformers!

1086

nicolas-dufour/miro

Python

Code for MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency

421

sunovivid/correction-training

Python

Official implementation of "Correction Training for Diffusion Models"

893

tang-bd/v-grpo

Python

[CVPR 2026 Findings] V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think

562

AndreasBergmeister/ram

Python
902

huggingface/finetrainers

Python

Scalable and memory-optimized training of diffusion models

1.4k139

SonyResearch/micro_diffusion

Python

Official repository for our work on micro-budget training of large-scale diffusion models.

1.6k59