5 papers
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…
End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
Yuwei Guo, Ceyuan Yang, Hao He +5
Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this vi…
ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions
Di Chang, Mingdeng Cao, Yichun Shi +7
Editing images with instructions to reflect non-rigid motions, camera viewpoint shifts, object deformations, human articulations, and complex interactions, poses a challenging yet…
SeedEdit 3.0: Fast and High-Quality Generative Image Editing
Peng Wang, Yichun Shi, Xiaochen Lian +5
We introduce SeedEdit 3.0, in companion with our T2I model Seedream 3.0, which significantly improves over our previous SeedEdit versions in both aspects of edit instruction follow…
Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
Zeqian Li, Shangzhe Di, Zhonghua Zhai +3
This paper presents a computational model for universal video temporal grounding, which accurately localizes temporal moments in videos based on natural language queries (e.g., que…