12 papers
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Yuqing Wang, Zhijie Lin, Ceyuan Yang +10
Unified multimodal models (UMMs) aim to handle perception and generation in a single model. Yet existing UMMs still rely on a frozen, separately pretrained VAE for image generation…
Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
Yanting Miao, Yutao Sun, Dexin Wang +8
Visual latent reasoning lets a multimodal large language model (MLLM) create intermediate visual evidence as continuous tokens, avoiding external tools or image generators. However…
RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation
Qi Zhao, Jun Chen, Ivor Tsang +1
While modern diffusion models excel at generating diverse single images, extending this to sequential generation reveals a fundamental challenge: balancing narrative dynamism with…
Context Unrolling in Omni Models
Ceyuan Yang, Zhijie Lin, Yang Zhao +16
We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such train…
VINCIE: Unlocking In-context Image Editing from Video
Leigang Qu, Feng Cheng, Ziyan Yang +7
In-context image editing aims to modify images based on a contextual sequence comprising text and previously generated images. Existing methods typically depend on task-specific pi…
SkipSR: Faster Super Resolution with Token Skipping
Rohan Choudhury, Shanchuan Lin, Jianyi Wang +6
Diffusion-based super-resolution (SR) is a key component in video generation and video restoration, but is slow and expensive, limiting scalability to higher resolutions and longer…