HanSaem Kim

kensaem's activity

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

upvoted an article about 6 hours ago

view article

Article

Training strategies of Z-Image-Turbo

• 

22 days ago

•

4

upvoted 2 papers about 14 hours ago

Deep Delta Learning

Paper • 2601.00417 • Published 5 days ago • 24

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Paper • 2601.00664 • Published 4 days ago • 44

upvoted a paper 4 days ago

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 6 days ago • 207

upvoted 7 papers 5 days ago

Guiding a Diffusion Transformer with the Internal Dynamics of Itself

Paper • 2512.24176 • Published 7 days ago • 7

ProEdit: Inversion-based Editing From Prompts Done Right

Paper • 2512.22118 • Published 11 days ago • 17

YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

Paper • 2512.23273 • Published 8 days ago • 13

SpotEdit: Selective Region Editing in Diffusion Transformers

Paper • 2512.22323 • Published 11 days ago • 37

Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

Paper • 2512.23705 • Published 8 days ago • 44

LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation

Paper • 2512.23576 • Published 8 days ago • 64

DreamOmni3: Scribble-based Editing and Generation

Paper • 2512.22525 • Published 10 days ago • 14

upvoted 2 papers 8 days ago

Spatia: Video Generation with Updatable Spatial Memory

Paper • 2512.15716 • Published 20 days ago • 29

HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming

Paper • 2512.21338 • Published 13 days ago • 21

upvoted 4 papers 9 days ago

DreaMontage: Arbitrary Frame-Guided One-Shot Video Generation

Paper • 2512.21252 • Published 13 days ago • 34

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 19 days ago • 91

SemanticGen: Video Generation in Semantic Space

Paper • 2512.20619 • Published 14 days ago • 89

SAM Audio: Segment Anything in Audio

Paper • 2512.18099 • Published 18 days ago • 21

upvoted 2 papers 14 days ago

StoryMem: Multi-shot Long Video Storytelling with Memory

Paper • 2512.19539 • Published 15 days ago • 17

WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion

Paper • 2512.19678 • Published 15 days ago • 29

upvoted a paper 15 days ago

StageVAR: Stage-Aware Acceleration for Visual Autoregressive Models

Paper • 2512.16483 • Published 19 days ago • 7