UMM-Reflection

Search everything

Mentions · 7d0
Mentions · 30d0
All mentions2
First seenSep 27, 2026
Last mentionedSep 28, 2026

Timeline

2 articles · newest first

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

UMM-Reflection uses interleaved RL so unified models repair their own image generations.

arXiv cs.AI / cs.LG / cs.CLSep 28, 17:59 UTC · Sep 28, 2026AI research1 · 1 read

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

UMM-Reflection trains one unified model with interleaved RL so reflection and image revisions improve together.

Hugging Face daily papersSep 27, 20:00 UTC · Sep 27, 2026AI research1 · 1 read

Appears with

BAGELai model · 2

Entities are extracted by the model from each article. First seen Sep 27, 2026, last mentioned Sep 28, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.