KlingAI Research

AI & ML interests

The Kling Team is building next-generation multimodal world models across video, audio, text, 3D, and beyond. We are continuously looking for exceptional talent to join us. Feel free to reach out!

Recent Activity

Makayi  submitted a paper about 16 hours ago

Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers

NinaKarine  submitted a paper 9 days ago

Multics: Generative Multi-Player World Model with Hierarchical Communication

vanzl  submitted a paper 11 days ago

DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

View all activity

Papers

Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers

TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback

View all Papers

Team members 35