arXiv 2610.12572 · cs.LG · 2026-10-08
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang, Pengfei Zhou, Wangbo Zhao, Fangyuan Kong, Pengfei Wan, Kun Gai and 1 more
KlingAI Research
In latest · #24 2026-W42 #7 Added on 2026-10-21
One-line takeaway
DiffusionART aggregates rewards before tilting the objective, making online RL fine-tuning of diffusion models efficient and stable.
DiffusionART 先聚合奖励再微调扩散模型，在线强化学习更高效也更稳定。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Visual generation
- MaLiang-Harness: A Programmable Path to Image and Video Generation ▲367
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation ▲364
- UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation ▲197
- Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds ▲182
- Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation ▲174
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.