8 papers · 1 filter
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Fengyi Fu, Mengqi Huang, Shaojin Wu +10
We present Lance, a lightweight native unified model supporting multimodal understanding, generation, and editing for both images and videos. Rather than relying on model capacity…
Stream-T1: Test-Time Scaling for Streaming Video Generation
Yijing Tu, Shaojin Wu, Mengqi Huang +4
While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on di…
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Bin Wu, Mengqi Huang, Shaojin Wu +4
Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the d…
UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
Yufeng Cheng, Wenxu Wu, Shaojin Wu +3
Recent advancements in image customization exhibit a wide range of application prospects due to stronger customization capabilities. However, since we humans are more sensitive to…
USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
Shaojin Wu, Mengqi Huang, Yufeng Cheng +5
Existing literature typically treats style-driven and subject-driven generation as two disjoint tasks: the former prioritizes stylistic similarity, whereas the latter insists on su…
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
Shaojin Wu, Mengqi Huang, Wenxu Wu +3
Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibi…
DreamO: A Unified Framework for Image Customization
Chong Mou, Yanze Wu, Wenxu Wu +15
Recently, extensive research on image customization (e.g., identity, subject, style, background, etc.) demonstrates strong customization capabilities in large-scale generative mode…
VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control
Shaojin Wu, Fei Ding, Mengqi Huang +2
While diffusion models show extraordinary talents in text-to-image generation, they may still fail to generate highly aesthetic images. More specifically, there is still a gap betw…