Reinforcement learning with three causal constraints enables multimodal models to internalize diagram-reasoning links in geometry, unlike SFT which only mimics surface format and harms performance.
Show-o: One single transformer to unify multimodal understanding and generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.
citing papers explorer
-
How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
Reinforcement learning with three causal constraints enables multimodal models to internalize diagram-reasoning links in geometry, unlike SFT which only mimics surface format and harms performance.
-
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.