Han-Bit Kang

hbkang's activity

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

upvoted 2 papers 4 days ago

Optimized Table Tokenization for Table Structure Recognition

Paper • 2305.03393 • Published May 5, 2023 • 1

PubTables-1M: Towards comprehensive table extraction from unstructured documents

Paper • 2110.00061 • Published Sep 30, 2021 • 3

upvoted a paper 18 days ago

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Paper • 2505.20161 • Published May 26 • 1

upvoted a paper 23 days ago

FineVision: Open Data Is All You Need

Paper • 2510.17269 • Published 25 days ago • 65

upvoted a paper 26 days ago

Image-GS: Content-Adaptive Image Representation via 2D Gaussians

Paper • 2407.01866 • Published Jul 2, 2024 • 1

upvoted a paper 28 days ago

BitNet Distillation

Paper • 2510.13998 • Published 30 days ago • 53

upvoted a paper about 1 month ago

Sequential Diffusion Language Models

Paper • 2509.24007 • Published Sep 28 • 44

upvoted a paper about 2 months ago

2D Gaussian Splatting with Semantic Alignment for Image Inpainting

Paper • 2509.01964 • Published Sep 2 • 6

upvoted a paper 2 months ago

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

Paper • 2509.00428 • Published Aug 30 • 17

upvoted 3 papers 3 months ago

Representing Speech Through Autoregressive Prediction of Cochlear Tokens

Paper • 2508.11598 • Published Aug 15 • 17

StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

Paper • 2508.11203 • Published Aug 15 • 10

HPSv3: Towards Wide-Spectrum Human Preference Score

Paper • 2508.03789 • Published Aug 5 • 19

upvoted 3 papers 4 months ago

FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers

Paper • 2507.12956 • Published Jul 17 • 24

FLEXITOKENS: Flexible Tokenization for Evolving Language Models

Paper • 2507.12720 • Published Jul 17 • 9

SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

Paper • 2507.09862 • Published Jul 14 • 49

upvoted 5 papers 5 months ago

Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation

Paper • 2506.19852 • Published Jun 24 • 41

Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images

Paper • 2506.22960 • Published Jun 28 • 6

HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling

Paper • 2506.20452 • Published Jun 25 • 19

Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model

Paper • 2506.15682 • Published Jun 18 • 5

JAFAR: Jack up Any Feature at Any Resolution

Paper • 2506.11136 • Published Jun 10 • 10