Han-Bit Kang

hbkang

AI & ML interests

Recent Activity

upvoted a paper 40 minutes ago

Forgetting Transformer: Softmax Attention with a Forget Gate

updated a collection 40 minutes ago

cool-papers

updated a collection about 3 hours ago

cool-papers

View all activity

Organizations

None yet

hbkang's activity

upvoted a paper 40 minutes ago

Forgetting Transformer: Softmax Attention with a Forget Gate

Paper • 2503.02130 • Published 6 days ago • 5

upvoted a paper about 3 hours ago

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

Paper • 2503.04724 • Published 3 days ago • 53

upvoted a paper 3 days ago

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

Paper • 2503.01933 • Published 7 days ago • 10

upvoted a paper 4 days ago

Large Language Diffusion Models

Paper • 2502.09992 • Published 24 days ago • 99

upvoted a paper 5 days ago

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

Paper • 2503.01063 • Published 7 days ago • 5

upvoted a paper 6 days ago

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

Paper • 2502.21318 • Published 9 days ago • 25

upvoted 2 papers 10 days ago

UniTok: A Unified Tokenizer for Visual Generation and Understanding

Paper • 2502.20321 • Published 10 days ago • 28

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

Paper • 2502.18417 • Published 12 days ago • 63

upvoted a paper 11 days ago

Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator

Paper • 2502.19204 • Published 12 days ago • 11

upvoted a paper 12 days ago

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

Paper • 2502.17363 • Published 13 days ago • 32

upvoted a paper 13 days ago

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

Paper • 2502.14397 • Published 18 days ago • 38

upvoted a paper 14 days ago

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

Paper • 2502.14786 • Published 17 days ago • 128

upvoted a paper 17 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 18 days ago

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

Paper • 2502.09509 • Published 24 days ago • 7

upvoted 2 papers 19 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 20 days ago • 4

upvoted a paper 25 days ago

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

Paper • 2502.07785 • Published 26 days ago • 11

upvoted a paper 28 days ago

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Paper • 2502.04320 • Published Feb 6 • 35

upvoted 2 papers about 1 month ago

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

Paper • 2502.01105 • Published Feb 3 • 20

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

Paper • 2502.01061 • Published Feb 3 • 186