4 papers
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
Xiaofeng Tan, Jun Liu, Bin-Bin Gao +5
RLHF is widely used to align flow-matching text-to-image models with human preferences, but often leads to severe diversity collapse after fine-tuning. In RL, diversity is often as…
Large-Scale Universal Defect Generation: Foundation Models and Datasets
Yuanting Fan, Jun Liu, Bin-Bin Gao +5
Existing defect/anomaly generation methods often rely on few-shot learning, which overfits to specific defect categories due to the lack of large-scale paired defect editing data.…
ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning
Xiaofeng Tan, Jun Liu, Yuanting Fan +7
Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment. However, they often introduce visual hallucinations like over-optimized details and semant…
Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection
Yuanting Fan, Jun Liu, Xiaochen Chen +5
Few-shot anomaly detection (FSAD) methods identify anomalous regions with few known normal samples. Most existing methods rely on the generalization ability of pre-trained vision-l…