HanSaem Kim

kensaem's activity

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

liked a model 3 days ago

Tongyi-MAI/Z-Image-Turbo

Text-to-Image • Updated 4 days ago • 170k • • 2.19k

upvoted 7 papers 5 days ago

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

Paper • 2511.22677 • Published 9 days ago • 18

Adversarial Flow Models

Paper • 2511.22475 • Published 9 days ago • 20

Vision Bridge Transformer at Scale

Paper • 2511.23199 • Published 8 days ago • 41

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published 9 days ago • 145

AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement

Paper • 2511.23475 • Published 8 days ago • 41

WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing

Paper • 2512.00387 • Published 8 days ago • 2

REASONEDIT: Towards Reasoning-Enhanced Image Editing Models

Paper • 2511.22625 • Published 9 days ago • 45

upvoted 2 papers 11 days ago

DoPE: Denoising Rotary Position Embedding

Paper • 2511.09146 • Published 24 days ago • 92

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

Paper • 2511.09611 • Published 24 days ago • 68

upvoted a collection 12 days ago

Kimi-VL-A3B

Collection

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 7 items • Updated Oct 30 • 77

upvoted 5 papers 12 days ago

A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space

Paper • 2511.10555 • Published 23 days ago • 60

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published 18 days ago • 222

Diversity Has Always Been There in Your Visual Autoregressive Models

Paper • 2511.17074 • Published 15 days ago • 7

SAM 3: Segment Anything with Concepts

Paper • 2511.16719 • Published 16 days ago • 105

WorldGen: From Text to Traversable and Interactive 3D Worlds

Paper • 2511.16825 • Published 16 days ago • 21

upvoted 2 papers 23 days ago

Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance

Paper • 2511.07499 • Published 26 days ago • 5

Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising

Paper • 2511.08633 • Published 27 days ago • 53

upvoted 2 papers 24 days ago

VideoSSR: Video Self-Supervised Reinforcement Learning

Paper • 2511.06281 • Published 28 days ago • 24

Dense Motion Captioning

Paper • 2511.05369 • Published 29 days ago • 9