Hyoung-Kyu Song PRO

deepkyu's activity

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

upvoted 2 papers about 10 hours ago

COMIC: Agentic Sketch Comedy Generation

Paper • 2603.11048 • Published 1 day ago • 3

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

Paper • 2603.03143 • Published 10 days ago • 133

liked a Space 5 days ago

Running

3.74k

The Ultra-Scale Playbook

🌌

3.74k

The ultimate guide to training LLM on large GPU Clusters

upvoted a paper 8 days ago

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 8 days ago • 159

upvoted a paper 17 days ago

Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control

Paper • 2602.18422 • Published 20 days ago • 30

upvoted an article 21 days ago

view article

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

• 
• 
• +4

21 days ago

•

483

upvoted a paper about 1 month ago

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published Jan 30 • 216

upvoted 2 papers 5 months ago

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17, 2025 • 49

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

Paper • 2510.15742 • Published Oct 17, 2025 • 51

liked a dataset 5 months ago

QingyanBai/Ditto-1M

Updated Oct 29, 2025 • 5.06k • 42

upvoted a paper 5 months ago

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

Paper • 2510.05684 • Published Oct 7, 2025 • 143

upvoted a paper 6 months ago

Lynx: Towards High-Fidelity Personalized Video Generation

Paper • 2509.15496 • Published Sep 19, 2025 • 13

upvoted a paper 8 months ago

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

Paper • 2506.23552 • Published Jun 30, 2025 • 10

liked a Space 8 months ago

Running on Zero

MCP

Featured

323

Chain-of-Zoom

🚀

323

Extreme Super-Resolution via Scale Autoregression

liked a model 8 months ago

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

Image-to-Image • Updated Jan 1 • 125k • • 2.56k

New activity in jt-zhang/SageAttention2_plus 9 months ago

It seems that sm90 cannot use sageattention2++ kernel

2

#2 opened 9 months ago by

kyunocap

authored a paper 9 months ago

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

Paper • 2506.08279 • Published Jun 9, 2025 • 27

commented a paper 9 months ago

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

Paper • 2506.08279 • Published Jun 9, 2025 • 27 •

2

upvoted a paper 9 months ago

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

Paper • 2506.08279 • Published Jun 9, 2025 • 27

commented a paper 12 months ago

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

Paper • 2504.00557 • Published Apr 1, 2025 • 15 •

2