Hyoung-Kyu Song

deepkyu's activity

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

upvoted a paper 20 days ago

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

Paper • 2506.23552 • Published 23 days ago • 9

liked a Space 21 days ago

Running on Zero

MCP

294

294

Chain-of-Zoom

🚀

Extreme Super-Resolution via Scale Autoregression

liked a model 21 days ago

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

Image-to-Image • Updated 25 days ago • 344k • • 1.78k

New activity in jt-zhang/SageAttention2_plus 23 days ago

It seems that sm90 cannot use sageattention2++ kernel

2

#2 opened 25 days ago by

kyunocap

authored a paper about 1 month ago

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

Paper • 2506.08279 • Published Jun 9 • 28

commented a paper about 1 month ago

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

Paper • 2506.08279 • Published Jun 9 • 28 •

2

upvoted a paper about 1 month ago

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

Paper • 2506.08279 • Published Jun 9 • 28

commented a paper 4 months ago

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

Paper • 2504.00557 • Published Apr 1 • 15 •

2

upvoted 2 papers 4 months ago

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

Paper • 2504.00557 • Published Apr 1 • 15

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

Paper • 2503.09641 • Published Mar 12 • 40

upvoted a collection 4 months ago

SANA-Sprint

Collection

🏃SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation • 6 items • Updated Apr 17 • 43

liked a Space 7 months ago

Running

552

552

The Tokenizer Playground

📝

Experiment with and compare different tokenizers

upvoted 5 papers 7 months ago

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

Paper • 2412.17739 • Published Dec 23, 2024 • 42

OpenAI o1 System Card

Paper • 2412.16720 • Published Dec 21, 2024 • 34

FastVLM: Efficient Vision Encoding for Vision Language Models

Paper • 2412.13303 • Published Dec 17, 2024 • 21

FashionComposer: Compositional Fashion Image Generation

Paper • 2412.14168 • Published Dec 18, 2024 • 16

Qwen2.5 Technical Report

Paper • 2412.15115 • Published Dec 19, 2024 • 369

liked 2 models 8 months ago

BadToBest/EchoMimicV2

Updated Jan 6 • 127

Lightricks/LTX-Video

Image-to-Video • Updated 6 days ago • 418k • 1.81k

liked a Space 8 months ago

Running

2.28k

2.28k

Anycoder

🏢

Generate HTML/CSS code for web designs