Kling Team

company

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

ChaosLiao authored a paper about 4 hours ago

ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine

DogNeverSleep submitted a paper about 17 hours ago

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

DogNeverSleep submitted a paper about 17 hours ago

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

View all activity

Papers

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

View all Papers

authored a paper about 4 hours ago

ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine

Paper • 2607.28625 • Published 2 days ago • 34

submitted 2 papers to Daily Papers about 17 hours ago

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

Paper • 2607.28509 • Published 2 days ago • 24

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Paper • 2607.28595 • Published 2 days ago • 44

published a model 1 day ago

KlingTeam/StreamHOI

Updated 1 day ago

authored a paper 8 days ago

Self Gradient Forcing: Native Long Video Extrapolation

Paper • 2607.20368 • Published 10 days ago • 34

updated a dataset 11 days ago

KlingTeam/CameraClone-Dataset

Viewer • Updated 11 days ago • 1.15M • 937 • 11

updated a model 11 days ago

KlingTeam/ShotStream

Text-to-Video • Updated 11 days ago • 16

authored 2 papers 11 days ago

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published 18 days ago • 108

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Paper • 2607.05382 • Published 23 days ago • 87

submitted 2 papers to Daily Papers 15 days ago

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

Paper • 2607.14189 • Published 17 days ago • 34

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Paper • 2607.14202 • Published 17 days ago • 42

submitted a paper to Daily Papers 16 days ago

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Paper • 2607.05382 • Published 23 days ago • 87

updated a model 17 days ago

KlingTeam/UnityVideo

Text-to-Video • Updated 17 days ago • 39 • 1

published a model 17 days ago

KlingTeam/UnityVideo

Text-to-Video • Updated 17 days ago • 39 • 1

updated a dataset 19 days ago

KlingTeam/UniBench

Viewer • Updated 19 days ago • 30.1k • 997 • 2

published a dataset 20 days ago

KlingTeam/UniBench

Viewer • Updated 19 days ago • 30.1k • 997 • 2

published a dataset about 1 month ago

KlingTeam/VWG-Bench

Viewer • Updated Jun 26 • 380 • 745 • 1

updated a dataset about 1 month ago

KlingTeam/VWG-Bench

Viewer • Updated Jun 26 • 380 • 745 • 1

authored a paper about 1 month ago

UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating

Paper • 2606.21661 • Published Jun 19 • 28

submitted a paper to Daily Papers about 1 month ago

UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating

Paper • 2606.21661 • Published Jun 19 • 28