Kyu Song

kyunocap's activity

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

upvoted a paper 1 day ago

AvatarPointillist: AutoRegressive 4D Gaussian Avatarization

Paper • 2604.04787 • Published 3 days ago • 8

upvoted a paper 3 days ago

Token Warping Helps MLLMs Look from Nearby Viewpoints

Paper • 2604.02870 • Published 6 days ago • 27

upvoted 3 papers 10 days ago

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

Paper • 2603.25716 • Published 14 days ago • 152

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Paper • 2603.25746 • Published 14 days ago • 154

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

Paper • 2603.25730 • Published 14 days ago • 51

upvoted a paper 12 days ago

AVControl: Efficient Framework for Training Audio-Visual Controls

Paper • 2603.24793 • Published 14 days ago • 26

upvoted a changelog 14 days ago

view changelog

Hugging Face Changelog

Introducing hf-mount

16 days ago

• 216

upvoted a paper 14 days ago

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

Paper • 2603.24440 • Published 15 days ago • 95

upvoted a paper 15 days ago

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published 17 days ago • 121

upvoted a paper 22 days ago

GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering

Paper • 2603.15616 • Published 24 days ago • 5

upvoted 3 papers 23 days ago

Attention Residuals

Paper • 2603.15031 • Published 24 days ago • 176

Mixture-of-Depths Attention

Paper • 2603.15619 • Published 24 days ago • 79

Grounding World Simulation Models in a Real-World Metropolis

Paper • 2603.15583 • Published 24 days ago • 153

upvoted a paper 24 days ago

OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

Paper • 2603.11647 • Published 28 days ago • 31

upvoted 3 papers 27 days ago

ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation

Paper • 2603.11421 • Published 28 days ago • 34

ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA

Paper • 2603.10256 • Published 29 days ago • 21

COMIC: Agentic Sketch Comedy Generation

Paper • 2603.11048 • Published 29 days ago • 4

upvoted a paper 28 days ago

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 30 days ago • 150

liked a model about 1 month ago

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated 25 days ago • 964k • • 1.43k

upvoted a paper about 1 month ago

The Trinity of Consistency as a Defining Principle for General World Models

Paper • 2602.23152 • Published Feb 26 • 201