11 papers
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss
Mingju Gao, Jingkai Zhou, Kun Gai +2
Fréchet distance has recently emerged as an effective distribution-level objective for generator post-training, complementing the conventional sample-level diffusion and flow-match…
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
Tianlin Pan, Lianyu Pang, Cheng Da +4
Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward…
Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
Yifu Luo, Haoyuan Sun, Xinhao Hu +12
Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is h…
Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback
Huaisong Zhang, Hao Yu, Yuxuan Zhang +7
Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requ…
MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training
Lianyu Pang, Tianlin Pan, Cheng Da +5
Representation alignment with pretrained vision models has recently shown strong potential for accelerating diffusion transformer training. By aligning intermediate diffusion featu…
RewardHarness: Self-Evolving Agentic Post-Training
Yuxuan Zhang, Penghui Du, Bo Li +11
Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation an…