Han-Bit Kang

hbkang

AI & ML interests

Recent Activity

updated a collection 1 day ago

ID-Preserving Generation

upvoted a paper 1 day ago

DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning

updated a collection 5 days ago

cool-papers

View all activity

Organizations

None yet

hbkang's activity

upvoted a paper 1 day ago

DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning

Paper • 2504.14509 • Published 6 days ago • 43

upvoted a paper 5 days ago

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Paper • 2504.13837 • Published 8 days ago • 99

upvoted a paper 10 days ago

Cobra: Efficient Line Art COlorization with BRoAder References

Paper • 2504.12240 • Published 10 days ago • 27

upvoted a paper 12 days ago

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Paper • 2504.08685 • Published 15 days ago • 121

upvoted a paper 17 days ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published 18 days ago • 73

upvoted 2 papers 18 days ago

TransMamba: Flexibly Switching between Transformer and Mamba

Paper • 2503.24067 • Published 26 days ago • 20

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 19 days ago • 172

upvoted 3 papers 19 days ago

Gaussian Mixture Flow Matching Models

Paper • 2504.05304 • Published 19 days ago • 12

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

Paper • 2504.03011 • Published 23 days ago • 10

HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration

Paper • 2504.03536 • Published 22 days ago • 13

upvoted a paper 20 days ago

Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation

Paper • 2504.02542 • Published 23 days ago • 42

upvoted a paper 23 days ago

Multi-Token Attention

Paper • 2504.00927 • Published 25 days ago • 46

upvoted a paper 24 days ago

Scaling Language-Free Visual Representation Learning

Paper • 2504.01017 • Published 25 days ago • 29

upvoted a paper 26 days ago

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

Paper • 2503.21732 • Published 30 days ago • 8

upvoted a paper 27 days ago

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model

Paper • 2503.21144 • Published about 1 month ago • 25

upvoted 2 papers 30 days ago

DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis

Paper • 2503.15667 • Published Mar 19 • 8

Scaling Vision Pre-Training to 4K Resolution

Paper • 2503.19903 • Published Mar 25 • 40

upvoted 3 papers about 1 month ago

BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation

Paper • 2503.20672 • Published Mar 26 • 14

Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models

Paper • 2503.20240 • Published Mar 26 • 22

Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

Paper • 2409.02634 • Published Sep 4, 2024 • 98