Kyu Song PRO

deepkyu's activity

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

upvoted a paper 21 days ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 25 days ago • 189

upvoted 2 collections about 1 month ago

Efficient Stable Diffusion

Collection

Block-removed Knowledge-distilled SD models; https://github.com/Nota-NetsPresso/BK-SDM • 9 items • Updated Jul 1, 2024 • 6

Efficient Solar Open Family

Collection

Solar Open models officially optimized by Nota AI for Korea’s government-led Sovereign AI initiative as part of the Upstage consortium. • 7 items • Updated 4 days ago • 26

upvoted 3 papers 5 months ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published Mar 26 • 158

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Paper • 2603.25746 • Published Mar 26 • 156

MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing

Paper • 2511.19963 • Published Nov 25, 2025 • 2

upvoted 5 papers 6 months ago

SegviGen: Repurposing 3D Generative Model for Part Segmentation

Paper • 2603.16869 • Published Mar 17 • 18

COMIC: Agentic Sketch Comedy Generation

Paper • 2603.11048 • Published Mar 11 • 5

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

Paper • 2603.03143 • Published Mar 3 • 144

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published Mar 4 • 190

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

Paper • 2602.18422 • Published Feb 20 • 30

upvoted an article 7 months ago

view article

Article

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

• 
• 
• +4

ggerganov, ngxson, allozaur, lysandre, victor, julien-c

•

Feb 20

• 510

upvoted a paper 7 months ago

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published Jan 30 • 230

upvoted 3 papers 11 months ago

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17, 2025 • 50

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

Paper • 2510.15742 • Published Oct 17, 2025 • 52

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

Paper • 2510.05684 • Published Oct 7, 2025 • 148

upvoted a paper 12 months ago

Lynx: Towards High-Fidelity Personalized Video Generation

Paper • 2509.15496 • Published Sep 19, 2025 • 13

upvoted 2 papers about 1 year ago

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

Paper • 2506.23552 • Published Jun 30, 2025 • 10

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

Paper • 2506.08279 • Published Jun 9, 2025 • 27

upvoted a paper over 1 year ago

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

Paper • 2504.00557 • Published Apr 1, 2025 • 15