activity
20242026
collaborators

11 papers

cs.CV2026

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…

cs.LG2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.AI2026

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…