arXiv 2609.35767 · cs.CV · 2026-09-28
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
Yijia Fan, Ziqi Huang, Zhongang Cai, Yan Li, Zimo Wen, Wanqi Yin, Haiwen Diao, Ziwei Liu
MMLab@NTU
In latest · #253 Added on 2026-10-21
One-line takeaway
Interleaved RL jointly trains reflection text and image generation so unified models can diagnose and repair their own images.
用交错强化学习联合训练统一多模态模型的“反思文本”和图像生成，让它能自查并修图。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Multimodal
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching ▲560
- LoopVL: Recurrent Visual Intelligence ▲417
- VideoJev: System One Model for Video Understanding and Interaction ▲375
- S-Space: Exploring Spatial Workspace in Multimodal Language Models ▲270
- UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement ▲266
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.