15 papers
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…
NativeTok: Native Visual Tokenization for Improved Image Generation
Bin Wu, Mengqi Huang, Weinan Jia +1
VQ-based image generation typically follows a two-stage pipeline: a tokenizer encodes images into discrete tokens, and a generative model learns their dependencies for reconstructi…
LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning
Fengyi Fu, Mengqi Huang, Lei Zhang +1
Text-driven multi-object image editing which aims to precisely modify multiple objects within an image based on text descriptions, has recently attracted considerable interest. Exi…
RealCustom++: Representing Images as Real Textual Word for Real-Time Customization
Zhendong Mao, Mengqi Huang, Fei Ding +3
Given a text and an image of a specific subject, text-to-image customization aims to generate new images that align with both the text and the subject's appearance. Existing works…
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…