Han-Bit Kang

hbkang's activity

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

upvoted a paper 1 day ago

RLDX-1 Technical Report

Paper • 2605.03269 • Published 3 days ago • 94

upvoted a paper 2 days ago

Soft Anisotropic Diagrams for Differentiable Image Representation

Paper • 2604.21984 • Published 11 days ago • 5

upvoted a paper 4 days ago

Representation Fréchet Loss for Visual Generation

Paper • 2604.28190 • Published 8 days ago • 28

upvoted a paper 9 days ago

Sapiens2

Paper • 2604.21681 • Published 15 days ago • 19

upvoted a paper 10 days ago

Video Analysis and Generation via a Semantic Progress Function

Paper • 2604.22554 • Published 14 days ago • 63

upvoted 2 papers 11 days ago

Coevolving Representations in Joint Image-Feature Diffusion

Paper • 2604.17492 • Published 19 days ago • 5

StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

Paper • 2604.21689 • Published 15 days ago • 25

upvoted a paper 22 days ago

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

Paper • 2604.05072 • Published 28 days ago • 18

upvoted a paper 24 days ago

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

Paper • 2604.10098 • Published 27 days ago • 79

upvoted 2 papers 28 days ago

LPM 1.0: Video-based Character Performance Model

Paper • 2604.07823 • Published 29 days ago • 77

GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos

Paper • 2604.07273 • Published about 1 month ago • 4

upvoted 6 papers about 1 month ago

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding

Paper • 2604.00886 • Published Apr 1 • 6

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published Mar 23 • 125

AVControl: Efficient Framework for Training Audio-Visual Controls

Paper • 2603.24793 • Published Mar 25 • 28

Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

Paper • 2603.25745 • Published Mar 26 • 16

4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video

Paper • 2603.21618 • Published Mar 23 • 15

Generalized Discrete Diffusion from Snapshots

Paper • 2603.21342 • Published Mar 22 • 11

upvoted 3 papers about 2 months ago

DROID-SLAM in the Wild

Paper • 2603.19076 • Published Mar 19 • 5

Grounding World Simulation Models in a Real-World Metropolis

Paper • 2603.15583 • Published Mar 16 • 153

Training Language Models via Neural Cellular Automata

Paper • 2603.10055 • Published Mar 9 • 8