Kun Xu
- Papers
- 8
Cite
Notes
Only stored in your browser.
8papers
Authored papers
8WideSeek: Advancing Wide Research via Multi-Agent Scaling
arXiv 2026
ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
arXiv 2026
Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
arXiv 2025
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
arXiv 2024
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
arXiv 2024
Harder Tasks Need More Experts: Dynamic Routing in MoE Models
arXiv 2024
Pyramidal Flow Matching for Efficient Video Generative Modeling
arXiv 2024
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 8 papers