Kyu Song

kyunocap's activity

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

liked a model 10 days ago

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated 14 days ago • 1.48M • • 1.28k

upvoted a paper 10 days ago

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

Paper • 2602.23152 • Published 11 days ago • 195

upvoted a paper 13 days ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published 14 days ago • 509

upvoted 4 papers 17 days ago

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Paper • 2602.06949 • Published about 1 month ago • 35

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published 24 days ago • 43

Unified Latents (UL): How to train your latents

Paper • 2602.17270 • Published 18 days ago • 57

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

Paper • 2602.16968 • Published 19 days ago • 12

upvoted 3 papers 19 days ago

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Paper • 2602.15547 • Published 20 days ago • 26

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Paper • 2602.12279 • Published 25 days ago • 20

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published 24 days ago • 54

liked a model 25 days ago

yaolily/TimeChat-Captioner-GRPO-7B

Video-Text-to-Text • 9B • Updated 26 days ago • 236 • 2

upvoted a paper about 1 month ago

3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation

Paper • 2602.03796 • Published Feb 3 • 62

upvoted an article about 1 month ago

view article

Article

We Got Claude to Build CUDA Kernels and teach open models!

• 
• 
• +2

Jan 28

•

147

upvoted 3 papers about 2 months ago

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published Jan 18 • 200

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 159

OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding

Paper • 2601.09575 • Published Jan 14 • 26

liked a model about 2 months ago

lovis93/next-scene-qwen-image-lora-2509

Image-to-Image • Updated Oct 21, 2025 • 35.7k • • 586

liked a Space about 2 months ago

Running on Zero

Featured

217

LTX-2 Video Fast

🎥

217

Fast high quality video with audio generation

upvoted 2 papers about 2 months ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published Jan 8 • 229

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Paper • 2601.05432 • Published Jan 8 • 168