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

CongWei1230 authored a paper 1 day ago

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

CongWei1230 submitted a paper 1 day ago

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Qinghew authored a paper 9 days ago

HappyWorld-Bench

View all activity

Papers

ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing

Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations

View all Papers

authored a paper 1 day ago

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Paper • 2609.38597 • Published 5 days ago • 13

submitted a paper to Daily Papers 1 day ago

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Paper • 2609.38597 • Published 5 days ago • 13

authored 3 papers 9 days ago

HappyWorld-Bench

Paper • 2609.24308 • Published 13 days ago • 57

Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models

Paper • 2603.22782 • Published Mar 24 • 19

Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA

Paper • 2603.08210 • Published Apr 1

submitted a paper to Daily Papers 10 days ago

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Paper • 2609.26774 • Published 12 days ago • 56

authored 5 papers 16 days ago

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 19 days ago • 146

No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs

Paper • 2606.31933 • Published Jun 30

Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning

Paper • 2602.00971 • Published Feb 28

Story2Proposal: A Scaffold for Structured Scientific Paper Writing

Paper • 2603.27065 • Published Mar 28 • 19

Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

Paper • 2509.11866 • Published Sep 15, 2025 • 2

updated a model 17 days ago

KlingTeam/ShotStream

Text-to-Video • Updated 17 days ago • 19

submitted a paper to Daily Papers 18 days ago

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 19 days ago • 146

authored a paper about 1 month ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published Aug 26 • 265

authored 3 papers about 1 month ago

TimePLE: Rethinking Temporal Representation for Video Temporal Grounding

Paper • 2607.23951 • Published Jul 27 • 1

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

Paper • 2607.23265 • Published Aug 3 • 1

CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning

Paper • 2606.24636 • Published Jun 23 • 3

updated a model about 2 months ago

KlingTeam/TimePLE

Image-Text-to-Text • 9B • Updated Aug 15 • 120 • 3

published a model about 2 months ago

KlingTeam/TimePLE

Image-Text-to-Text • 9B • Updated Aug 15 • 120 • 3

published a dataset about 2 months ago

KlingTeam/TimePLE-Dataset

Preview • Updated Aug 15 • 588 • 5