85 citations · 482 across the 58 of their papers we have counts for
8 papers · 1 filter
Transforming Image Editors into Video Editors
Feng Wang, Zijie Li, Ceyuan Yang +2
Recent image editing systems have achieved impressive semantic understanding, visual fidelity, and instruction-following ability, while video editing remains substantially more dif…
VoT: Vision-of-Thought for Unified Multimodal Representation Alignment
Jingxiang Sun, Chao Liao, Zhengxiong Luo +6
Current text-to-image systems typically employ a "text encoder plus diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise. Despite their su…
Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning
Jiahao Shao, Yuanbo Yang, Yiyi Liao +3
Tool-augmented vision-language models increasingly "think with images": they call crop, zoom, or code tools and reason over the returned pixels. However, recent work using blind te…
Explicit Critic Guidance for Aligning Diffusion Models
Zhengyang Liang, Qihang Zhang, Ceyuan Yang
Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations…
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…
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…
Continuous Adversarial Flow Models
Shanchuan Lin, Ceyuan Yang, Zhijie Lin +2
We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which uses a fixed mean-squared-err…
VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
Feng Wang, Yichun Shi, Ceyuan Yang +4
This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokeni…