5 papers
EditCaption: Human-Refined SFT and HAE-DPO for Image Editing Instruction Synthesis
Xiangyuan Wang, Honghao Cai, Yunhao Bai +9
High-quality source-target image pairs with precise editing instructions are essential for instruction-guided image editing, yet constructing such training triplets at scale remain…
IdGlow: Dynamic Identity Modulation for Multi-Subject Generation
Honghao Cai, Xiangyuan Wang, Jing Li +15
Multi-subject image generation requires seamlessly harmonizing multiple reference identities within a coherent scene. However, existing methods relying on rigid spatial masks or lo…
Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing
Honghao Cai, Xiangyuan Wang, Yunhao Bai +8
Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-attention architectures offer no…
PROMO: Promptable Outfitting for Efficient High-Fidelity Virtual Try-On
Haohua Chen, Tianze Zhou, Wei Zhu +8
Virtual Try-on (VTON) has become a core capability for online retail, where realistic try-on results provide reliable fit guidance, reduce returns, and benefit both consumers and m…
Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards
Zhaohui Jiang, Xuening Feng, Paul Weng +6
In practice, reinforcement learning (RL) agents are often trained with a possibly imperfect proxy reward function, which may lead to a human-agent alignment issue (i.e., the learne…