Han-Bit Kang

hbkang

AI & ML interests

Recent Activity

updated a collection about 16 hours ago

cool-papers

updated a collection about 16 hours ago

interesting architecture

upvoted a paper about 16 hours ago

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

View all activity

Organizations

None yet

hbkang's activity

upvoted a paper about 16 hours ago

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Paper • 2503.09573 • Published 1 day ago • 27

upvoted a paper about 18 hours ago

AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models

Paper • 2503.08417 • Published 2 days ago • 6

upvoted a paper 3 days ago

ProReflow: Progressive Reflow with Decomposed Velocity

Paper • 2503.04824 • Published 9 days ago • 9

upvoted 2 papers 4 days ago

Forgetting Transformer: Softmax Attention with a Forget Gate

Paper • 2503.02130 • Published 10 days ago • 26

LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

Paper • 2503.04724 • Published 7 days ago • 59

upvoted a paper 7 days ago

Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective

Paper • 2503.01933 • Published 11 days ago • 11

upvoted a paper 8 days ago

Large Language Diffusion Models

Paper • 2502.09992 • Published 27 days ago • 103

upvoted a paper 9 days ago

AI-Invented Tonal Languages: Preventing a Machine Lingua Franca Beyond Human Understanding

Paper • 2503.01063 • Published 11 days ago • 5

upvoted a paper 10 days ago

How far can we go with ImageNet for Text-to-Image generation?

Paper • 2502.21318 • Published 13 days ago • 25

upvoted 2 papers 14 days ago

UniTok: A Unified Tokenizer for Visual Generation and Understanding

Paper • 2502.20321 • Published 14 days ago • 29

GHOST 2.0: generative high-fidelity one shot transfer of heads

Paper • 2502.18417 • Published 16 days ago • 63

upvoted 2 papers 15 days ago

Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator

Paper • 2502.19204 • Published 15 days ago • 11

KV-Edit: Training-Free Image Editing for Precise Background Preservation

Paper • 2502.17363 • Published 17 days ago • 33

upvoted a paper 17 days ago

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data

Paper • 2502.14397 • Published 21 days ago • 38

upvoted a paper 18 days ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 21 days ago • 129

upvoted a paper 21 days ago

InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation

Paper • 2407.00788 • Published Jun 30, 2024 • 24

upvoted a paper 22 days ago

EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling

Paper • 2502.09509 • Published 28 days ago • 7

upvoted 2 papers 23 days ago

EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

Paper • 2404.19110 • Published Apr 29, 2024 • 4

Diffusion Models without Classifier-free Guidance

Paper • 2502.12154 • Published 24 days ago • 4

upvoted a paper 29 days ago

Pippo: High-Resolution Multi-View Humans from a Single Image

Paper • 2502.07785 • Published about 1 month ago • 11