SUDER uses the likelihood of reconstructing the original input from a sampled output as a self-reward, improving both understanding and generation in unified multimodal models without external supervision.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
SUDER uses the likelihood of reconstructing the original input from a sampled output as a self-reward, improving both understanding and generation in unified multimodal models without external supervision.