Gazer uses MLLM feedback in two stages to diagnose semantic errors in intermediate AVM states and rewind/rectify the generation trajectory, improving alignment on compositional benchmarks without training.
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization , url =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Training-Free Semantic Correction for Autoregressive Visual Models
Gazer uses MLLM feedback in two stages to diagnose semantic errors in intermediate AVM states and rewind/rectify the generation trajectory, improving alignment on compositional benchmarks without training.