3 papers
cs.CV2026
VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
Zhong-Yu Li, Ruoyi Du, Juncheng Yan +6
Recent progress in diffusion models significantly advances various image generation tasks. However, the current mainstream approach remains focused on building task-specific models…
cs.CV2025
OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better
Yupeng Zhou, Zhen Li, Ziheng Ouyang +8
Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compare…
cs.CV2025
OmniCaptioner: One Captioner to Rule Them All
Yiting Lu, Jiakang Yuan, Zhen Li +17
We propose OmniCaptioner, a versatile visual captioning framework for generating fine-grained textual descriptions across a wide variety of visual domains. Unlike prior methods lim…