Li

kotion's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 6 days ago

FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing

Paper • 2604.22586 • Published 9 days ago • 16

upvoted a paper 6 days ago

FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing

Paper • 2604.22586 • Published 9 days ago • 16

upvoted a paper 16 days ago

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Paper • 2604.14268 • Published 18 days ago • 117

upvoted 6 papers 17 days ago

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Paper • 2604.08995 • Published 23 days ago • 49

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation

Paper • 2604.10030 • Published 22 days ago • 15

Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

Paper • 2604.08121 • Published 24 days ago • 43

OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation

Paper • 2604.11804 • Published 20 days ago • 71

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published 22 days ago • 78

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

Paper • 2604.12887 • Published 19 days ago • 5

liked 2 models 18 days ago

baidu/ERNIE-Image-Turbo

Text-to-Image • Updated 16 days ago • 15k • • 369

baidu/ERNIE-Image

Text-to-Image • Updated 16 days ago • 9.75k • • 598

updated a dataset 3 months ago

CUC-MIPG/IC-Effect

Preview • Updated Jan 29 • 191

updated a model 3 months ago

CUC-MIPG/IC-Effect

Updated Jan 27

published a dataset 3 months ago

CUC-MIPG/IC-Effect

Preview • Updated Jan 29 • 191

published a model 3 months ago

CUC-MIPG/IC-Effect

Updated Jan 27

upvoted a paper 4 months ago

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

Paper • 2601.03193 • Published Jan 6 • 50

upvoted a paper 5 months ago

Generative Neural Video Compression via Video Diffusion Prior

Paper • 2512.05016 • Published Dec 4, 2025 • 10

authored a paper 5 months ago

IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning

Paper • 2512.15635 • Published Dec 17, 2025 • 20

upvoted 2 papers 5 months ago

IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning

Paper • 2512.15635 • Published Dec 17, 2025 • 20

UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

Paper • 2512.07831 • Published Dec 8, 2025 • 17