7 papers
Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
Siming Fu, Haojun Xu, Ruizhe He +9
Leading open text-to-image models often carry complementary strengths: one may lead on preference-aligned aesthetics while another follows compositional instructions more faithfull…
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
Siming Fu, Zheming Fu, Ruizhe He +7
On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, match…
Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation
Binyuan Huang, Yuning Lu, Weinan Jia +3
Recent proprietary models such as Sora2 demonstrate promising progress in generating multi-shot videos conditioned on multiple reference characters. However, academic research on t…
MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation
Weinan Jia, Yuning Lu, Mengqi Huang +6
Long video generation with Diffusion Transformers (DiTs) is bottlenecked by the quadratic scaling of full attention with sequence length. Since attention is highly redundant, outpu…
MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
Dong She, Siming Fu, Mushui Liu +4
Multi-subject personalized generation presents unique challenges in maintaining identity fidelity and semantic coherence when synthesizing images conditioned on multiple reference…
FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
Qiaoqiao Jin, Siming Fu, Dong She +4
Multi-subject personalized image generation aims to synthesize customized images containing multiple specified subjects without requiring test-time optimization. However, achieving…