5 citations · 13 across the 6 of their papers we have counts for
7 papers
Learning from Next-Frame Prediction: Towards Unified and Scalable Visual World Modeling
Yifeng Yao, Jinghan Li, Zhihao Zhang +5
Video provides a natural source of supervision: what happens next serves as a learning signal for visual world modeling. Yet masked video pretraining focuses on recovering missing…
Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
Jinghan Li, Yang Jin, Hao Jiang +3
Recent advances in pretraining general foundation models have significantly improved performance across diverse downstream tasks. While autoregressive (AR) generative models like G…
Pyramidal Flow Matching for Efficient Video Generative Modeling
Yang Jin, Zhicheng Sun, Ningyuan Li +7
Video generation requires modeling a vast spatiotemporal space, which demands significant computational resources and data usage. To reduce the complexity, the prevailing approache…
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Zhicheng Sun, Zhenhao Yang, Yang Jin +7
Customizing diffusion models to generate identity-preserving images from user-provided reference images is an intriguing new problem. The prevalent approaches typically require tra…
Harder Tasks Need More Experts: Dynamic Routing in MoE Models
Quzhe Huang, Zhenwei An, Nan Zhuang +7
In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adju…
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
Yang Jin, Zhicheng Sun, Kun Xu +9
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Co…
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Yang Jin, Kun Xu, Liwei Chen +12
Recently, the remarkable advance of the Large Language Model (LLM) has inspired researchers to transfer its extraordinary reasoning capability to both vision and language data. How…