Hyoung-Kyu Song

deepkyu's activity

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

upvoted 2 papers about 2 months ago

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17 • 48

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Paper • 2510.15742 • Published Oct 17 • 50

liked a dataset about 2 months ago

QingyanBai/Ditto-1M

Updated Oct 29 • 7.56k • 37

upvoted a paper about 2 months ago

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Paper • 2510.05684 • Published Oct 7 • 141

upvoted a paper 3 months ago

Lynx: Towards High-Fidelity Personalized Video Generation

Paper • 2509.15496 • Published Sep 19 • 12

upvoted a paper 5 months ago

JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching

Paper • 2506.23552 • Published Jun 30 • 11

liked a Space 5 months ago

Running on Zero

MCP

Featured

314

Chain-of-Zoom

🚀

314

Extreme Super-Resolution via Scale Autoregression

liked a model 5 months ago

black-forest-labs/FLUX.1-Kontext-dev

Image-to-Image • Updated Jun 27 • 321k • • 2.46k

New activity in jt-zhang/SageAttention2_plus 5 months ago

It seems that sm90 cannot use sageattention2++ kernel

2

#2 opened 5 months ago by

kyunocap

authored a paper 6 months ago

Seeing Voices: Generating A-Roll Video from Audio with Mirage

Paper • 2506.08279 • Published Jun 9 • 27

commented a paper 6 months ago

Seeing Voices: Generating A-Roll Video from Audio with Mirage

Paper • 2506.08279 • Published Jun 9 • 27 •

2

upvoted a paper 6 months ago

Seeing Voices: Generating A-Roll Video from Audio with Mirage

Paper • 2506.08279 • Published Jun 9 • 27

commented a paper 8 months ago

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

Paper • 2504.00557 • Published Apr 1 • 15 •

2

upvoted a paper 8 months ago

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

Paper • 2504.00557 • Published Apr 1 • 15

upvoted a paper 9 months ago

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Paper • 2503.09641 • Published Mar 12 • 41

upvoted a collection 9 months ago

SANA-Sprint

Collection

🏃SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation • 6 items • Updated Sep 13 • 43

liked a Space 11 months ago

Running

Featured

606

The Tokenizer Playground

📝

606

Experiment with and compare different tokenizers

upvoted 3 papers 12 months ago

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization

Paper • 2412.17739 • Published Dec 23, 2024 • 41

OpenAI o1 System Card

Paper • 2412.16720 • Published Dec 21, 2024 • 36

FastVLM: Efficient Vision Encoding for Vision Language Models

Paper • 2412.13303 • Published Dec 17, 2024 • 72